Delete .github/workflows/no-response.yml

* add cog.yaml

* add cog predict

* add cog predict

* update cog predict

* update cog predict

* add alpha png

* update cog predict

* update cog predict

* update cog predict

* update readme

* fix codespell

.github/workflows/no-response.yml

@@ -1,34 +0,0 @@
-name: No Response
-
-# Modified from: https://raw.githubusercontent.com/github/docs/main/.github/workflows/no-response.yaml
-
-# **What it does**: Closes issues that don't have enough information to be
-#                   actionable.
-# **Why we have it**: To remove the need for maintainers to remember to check
-#                     back on issues periodically to see if contributors have
-#                     responded.
-# **Who does it impact**: Everyone that works on docs or docs-internal.
-
-on:
-  issue_comment:
-    types: [created]
-
-  schedule:
-    # Schedule for five minutes after the hour every hour
-    - cron: '5 * * * *'
-
-jobs:
-  noResponse:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: lee-dohm/no-response@v0.5.0
-        with:
-          token: ${{ github.token }}
-          closeComment: >
-            This issue has been automatically closed because there has been no response
-            to our request for more information from the original author. With only the
-            information that is currently in the issue, we don't have enough information
-            to take action. Please reach out if you have or find the answers we need so
-            that we can investigate further.
-            If you still have questions, please improve your description and re-open it.
-            Thanks :-)

.github/workflows/publish-pip.yml

@@ -18,12 +18,15 @@ jobs:
       - name: Install PyTorch (cpu)
         run: pip install torch==1.7.0+cpu torchvision==0.8.1+cpu -f https://download.pytorch.org/whl/torch_stable.html
       - name: Install dependencies
-        run: pip install -r requirements.txt
+        run: |
+          pip install basicsr
+          pip install facexlib
+          pip install gfpgan
+          pip install -r requirements.txt
       - name: Build and install
         run: rm -rf .eggs && pip install -e .
       - name: Build for distribution
-        # remove bdist_wheel for pip installation with compiling cuda extensions
+        run: python setup.py sdist bdist_wheel
-        run: python setup.py sdist
       - name: Publish distribution to PyPI
         uses: pypa/gh-action-pypi-publish@master
         with:

.github/workflows/pylint.yml

@@ -20,11 +20,12 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install flake8 yapf isort
+        pip install codespell flake8 isort yapf
 
     # modify the folders accordingly
     - name: Lint
       run: |
+        codespell
         flake8 .
         isort --check-only --diff realesrgan/ scripts/ inference_realesrgan.py setup.py
         yapf -r -d realesrgan/ scripts/ inference_realesrgan.py setup.py

.github/workflows/release.yml

@@ -0,0 +1,41 @@
+name: release
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build:
+    permissions: write-all
+    name: Create Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Create Release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: Real-ESRGAN ${{ github.ref }} Release Note
+          body: |
+            🚀 See you again 😸
+            🚀Have a nice day 😸 and happy everyday 😃
+            🚀 Long time no see ☄️
+
+            ✨ **Highlights**
+            ✅ [Features] Support ...
+
+            🐛 **Bug Fixes**
+
+            🌴 **Improvements**
+
+            📢📢📢
+
+            <p align="center">
+               <img src="https://raw.githubusercontent.com/xinntao/Real-ESRGAN/master/assets/realesrgan_logo.png" height=150>
+            </p>
+          draft: true
+          prerelease: false

.gitignore

@@ -5,7 +5,7 @@ results/*
 tb_logger/*
 wandb/*
 tmp/*
-realesrgan/weights/*
+weights/*
 
 version.py
 

.pre-commit-config.yaml

@@ -24,6 +24,12 @@ repos:
     hooks:
       - id: yapf
 
+  # codespell
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.1.0
+    hooks:
+      - id: codespell
+
   # pre-commit-hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.2.0

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+xintao.wang@outlook.com or xintaowang@tencent.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

FAQ.md

@@ -1,9 +0,0 @@
-# FAQ
-
-1. **What is the difference of `--netscale` and `outscale`?**
-
-A: TODO.
-
-1. **How to select models?**
-
-A: TODO.

MANIFEST.in

@@ -5,4 +5,4 @@ include inference_realesrgan.py
 include VERSION
 include LICENSE
 include requirements.txt
-include realesrgan/weights/README.md
+include weights/README.md

README.md

@@ -1,38 +1,54 @@
-# Real-ESRGAN
+<p align="center">
+  <img src="assets/realesrgan_logo.png" height=120>
+</p>
+
+## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
+
+<div align="center">
+
+👀[**Demos**](#-demos-videos) **|** 🚩[**Updates**](#-updates) **|** ⚡[**Usage**](#-quick-inference) **|** 🏰[**Model Zoo**](docs/model_zoo.md) **|** 🔧[Install](#-dependencies-and-installation)  **|** 💻[Train](docs/Training.md) **|** ❓[FAQ](docs/FAQ.md) **|** 🎨[Contribution](docs/CONTRIBUTING.md)
 
 [![download](https://img.shields.io/github/downloads/xinntao/Real-ESRGAN/total.svg)](https://github.com/xinntao/Real-ESRGAN/releases)
 [![PyPI](https://img.shields.io/pypi/v/realesrgan)](https://pypi.org/project/realesrgan/)
-[![Open issue](https://isitmaintained.com/badge/open/xinntao/Real-ESRGAN.svg)](https://github.com/xinntao/Real-ESRGAN/issues)
+[![Open issue](https://img.shields.io/github/issues/xinntao/Real-ESRGAN)](https://github.com/xinntao/Real-ESRGAN/issues)
+[![Closed issue](https://img.shields.io/github/issues-closed/xinntao/Real-ESRGAN)](https://github.com/xinntao/Real-ESRGAN/issues)
 [![LICENSE](https://img.shields.io/github/license/xinntao/Real-ESRGAN.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE)
 [![python lint](https://github.com/xinntao/Real-ESRGAN/actions/workflows/pylint.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/pylint.yml)
 [![Publish-pip](https://github.com/xinntao/Real-ESRGAN/actions/workflows/publish-pip.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/publish-pip.yml)
 
-1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN <a href="https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>.
+</div>
-2. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#Portable-executable-files).
 
-Real-ESRGAN aims at developing **Practical Algorithms for General Image Restoration**.<br>
+🔥 **AnimeVideo-v3 model (动漫视频小模型)**. Please see [[*anime video models*](docs/anime_video_model.md)] and [[*comparisons*](docs/anime_comparisons.md)]<br>
+🔥 **RealESRGAN_x4plus_anime_6B** for anime images **(动漫插图模型)**. Please see [[*anime_model*](docs/anime_model.md)]
+
+<!-- 1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B) -->
+1. :boom: **Update** online Replicate demo: [![Replicate](https://img.shields.io/static/v1?label=Demo&message=Replicate&color=blue)](https://replicate.com/xinntao/realesrgan)
+1. Online Colab demo for Real-ESRGAN: [![Colab](https://img.shields.io/static/v1?label=Demo&message=Colab&color=orange)](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) **|** Online Colab demo for for Real-ESRGAN (**anime videos**): [![Colab](https://img.shields.io/static/v1?label=Demo&message=Colab&color=orange)](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing)
+1. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#portable-executable-files-ncnn). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
+<!-- 1. You can watch enhanced animations in [Tencent Video](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html). 欢迎观看[腾讯视频动漫修复](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html) -->
+
+Real-ESRGAN aims at developing **Practical Algorithms for General Image/Video Restoration**.<br>
 We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.
 
-:question: Frequently Asked Questions can be found in [FAQ.md](FAQ.md).
+🌌 Thanks for your valuable feedbacks/suggestions. All the feedbacks are updated in [feedback.md](docs/feedback.md).
-
-:triangular_flag_on_post: **Updates**
-- :white_check_mark: Integrate [GFPGAN](https://github.com/TencentARC/GFPGAN) to support **face enhancement**.
-- :white_check_mark: Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/Real-ESRGAN).
-- :white_check_mark: Support arbitrary scale with `--outscale` (It actually further resizes outputs with `LANCZOS4`). Add *RealESRGAN_x2plus.pth* model.
-- :white_check_mark: [The inference code](inference_realesrgan.py) supports: 1) **tile** options; 2) images with **alpha channel**; 3) **gray** images; 4) **16-bit** images.
-- :white_check_mark: The training codes have been released. A detailed guide can be found in [Training.md](Training.md).
-
-If Real-ESRGAN is helpful in your photos/projects, please help to :star: this repo. Thanks:blush: <br>
-Other recommended projects: &emsp; :arrow_forward: [GFPGAN](https://github.com/TencentARC/GFPGAN) &emsp; :arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR) &emsp; :arrow_forward: [facexlib](https://github.com/xinntao/facexlib)
 
 ---
 
-### :book: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
+If Real-ESRGAN is helpful, please help to ⭐ this repo or recommend it to your friends 😊 <br>
+Other recommended projects:<br>
+▶️ [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>
+▶️ [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>
+▶️ [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>
+▶️ [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison <br>
+▶️ [HandyFigure](https://github.com/xinntao/HandyFigure): Open source of paper figures <br>
 
-> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [Project Page] &emsp; [Demo] <br>
+---
+
+### 📖 Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
+
+> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [[YouTube Video](https://www.youtube.com/watch?v=fxHWoDSSvSc)] &emsp; [[B站讲解](https://www.bilibili.com/video/BV1H34y1m7sS/)] &emsp; [[Poster](https://xinntao.github.io/projects/RealESRGAN_src/RealESRGAN_poster.pdf)] &emsp; [[PPT slides](https://docs.google.com/presentation/d/1QtW6Iy8rm8rGLsJ0Ldti6kP-7Qyzy6XL/edit?usp=sharing&ouid=109799856763657548160&rtpof=true&sd=true)]<br>
 > [Xintao Wang](https://xinntao.github.io/), Liangbin Xie, [Chao Dong](https://scholar.google.com.hk/citations?user=OSDCB0UAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>
-> Applied Research Center (ARC), Tencent PCG<br>
+> [Tencent ARC Lab](https://arc.tencent.com/en/ai-demos/imgRestore); Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
-> Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
 
 <p align="center">
   <img src="assets/teaser.jpg">
@@ -40,54 +56,35 @@ Other recommended projects: &emsp; :arrow_forward: [GFPGAN](https://github.com/T
 
 ---
 
-We have provided a pretrained model (*RealESRGAN_x4plus.pth*) with upsampling X4.<br>
+<!---------------------------------- Updates --------------------------->
-**Note that RealESRGAN may still fail in some cases as the real-world degradations are really too complex.**<br>
+## 🚩 Updates
-Moreover, it **may not** perform well on **human faces, text**, *etc*, which will be optimized later.
-<br>
 
-Real-ESRGAN will be a long-term supported project (in my current plan :smiley:). It will be continuously updated
+- ✅ Add the **realesr-general-x4v3** model - a tiny small model for general scenes. It also supports the **-dn** option to balance the noise (avoiding over-smooth results). **-dn** is short for denoising strength.
-in my spare time.
+- ✅ Update the **RealESRGAN AnimeVideo-v3** model. Please see [anime video models](docs/anime_video_model.md) and [comparisons](docs/anime_comparisons.md) for more details.
-
+- ✅ Add small models for anime videos. More details are in [anime video models](docs/anime_video_model.md).
-Here is a TODO list in the near future:
+- ✅ Add the ncnn implementation [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
-
+- ✅ Add [*RealESRGAN_x4plus_anime_6B.pth*](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth), which is optimized for **anime** images with much smaller model size. More details and comparisons with [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan) are in [**anime_model.md**](docs/anime_model.md)
-- [ ] optimize for human faces
+- ✅ Support finetuning on your own data or paired data (*i.e.*, finetuning ESRGAN). See [here](docs/Training.md#Finetune-Real-ESRGAN-on-your-own-dataset)
-- [ ] optimize for texts
+- ✅ Integrate [GFPGAN](https://github.com/TencentARC/GFPGAN) to support **face enhancement**.
-- [ ] optimize for anime images [in progress]
+- ✅ Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/Real-ESRGAN). Thanks [@AK391](https://github.com/AK391)
-- [ ] support more scales
+- ✅ Support arbitrary scale with `--outscale` (It actually further resizes outputs with `LANCZOS4`). Add *RealESRGAN_x2plus.pth* model.
-- [ ] support controllable restoration strength
+- ✅ [The inference code](inference_realesrgan.py) supports: 1) **tile** options; 2) images with **alpha channel**; 3) **gray** images; 4) **16-bit** images.
-
+- ✅ The training codes have been released. A detailed guide can be found in [Training.md](docs/Training.md).
-If you have any good ideas or demands, please open an issue/discussion to let me know. <br>
-If you have some images that Real-ESRGAN could not well restored, please also open an issue/discussion. I will record it (but I cannot guarantee to resolve it:stuck_out_tongue:). If necessary, I will open a page to specially record these real-world cases that need to be solved, but the current technology is difficult to handle well.
 
 ---
 
-### Portable executable files
+<!---------------------------------- Demo videos --------------------------->
+## 👀 Demos Videos
 
-You can download [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.2/realesrgan-ncnn-vulkan-20210801-macos.zip) **executable files for Intel/AMD/Nvidia GPU**.
+#### Bilibili
 
-This executable file is **portable** and includes all the binaries and models required. No CUDA or PyTorch environment is needed.<br>
+- [大闹天宫片段](https://www.bilibili.com/video/BV1ja41117zb)
+- [Anime dance cut 动漫魔性舞蹈](https://www.bilibili.com/video/BV1wY4y1L7hT/)
+- [海贼王片段](https://www.bilibili.com/video/BV1i3411L7Gy/)
 
-You can simply run the following command (the Windows example, more information is in the README.md of each executable files):
+#### YouTube
 
-```bash
+## 🔧 Dependencies and Installation
-./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png
-```
-
-We have provided three models:
-
-1. realesrgan-x4plus  (default)
-2. realesrnet-x4plus
-3. esrgan-x4
-
-You can use the `-n` argument for other models, for example, `./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrnet-x4plus`
-
-Note that it may introduce block inconsistency (and also generate slightly different results from the PyTorch implementation), because this executable file first crops the input image into several tiles, and then processes them separately, finally stitches together.
-
-This executable file is based on the wonderful [Tencent/ncnn](https://github.com/Tencent/ncnn) and [realsr-ncnn-vulkan](https://github.com/nihui/realsr-ncnn-vulkan) by [nihui](https://github.com/nihui).
-
----
-
-## :wrench: Dependencies and Installation
 
 - Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
 - [PyTorch >= 1.7](https://pytorch.org/)
@@ -114,44 +111,162 @@ This executable file is based on the wonderful [Tencent/ncnn](https://github.com
     python setup.py develop
     ```
 
-## :zap: Quick Inference
+---
+
+## ⚡ Quick Inference
+
+There are usually three ways to inference Real-ESRGAN.
+
+1. [Online inference](#online-inference)
+1. [Portable executable files (NCNN)](#portable-executable-files-ncnn)
+1. [Python script](#python-script)
+
+### Online inference
+
+1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B)
+1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN **|** [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**).
+
+### Portable executable files (NCNN)
+
+You can download [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**.
+
+This executable file is **portable** and includes all the binaries and models required. No CUDA or PyTorch environment is needed.<br>
+
+You can simply run the following command (the Windows example, more information is in the README.md of each executable files):
+
+```bash
+./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n model_name
+```
+
+We have provided five models:
+
+1. realesrgan-x4plus  (default)
+2. realesrnet-x4plus
+3. realesrgan-x4plus-anime (optimized for anime images, small model size)
+4. realesr-animevideov3 (animation video)
+
+You can use the `-n` argument for other models, for example, `./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrnet-x4plus`
+
+#### Usage of portable executable files
+
+1. Please refer to [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan#computer-usages) for more details.
+1. Note that it does not support all the functions (such as `outscale`) as the python script `inference_realesrgan.py`.
+
+```console
+Usage: realesrgan-ncnn-vulkan.exe -i infile -o outfile [options]...
+
+  -h                   show this help
+  -i input-path        input image path (jpg/png/webp) or directory
+  -o output-path       output image path (jpg/png/webp) or directory
+  -s scale             upscale ratio (can be 2, 3, 4. default=4)
+  -t tile-size         tile size (>=32/0=auto, default=0) can be 0,0,0 for multi-gpu
+  -m model-path        folder path to the pre-trained models. default=models
+  -n model-name        model name (default=realesr-animevideov3, can be realesr-animevideov3 | realesrgan-x4plus | realesrgan-x4plus-anime | realesrnet-x4plus)
+  -g gpu-id            gpu device to use (default=auto) can be 0,1,2 for multi-gpu
+  -j load:proc:save    thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu
+  -x                   enable tta mode"
+  -f format            output image format (jpg/png/webp, default=ext/png)
+  -v                   verbose output
+```
+
+Note that it may introduce block inconsistency (and also generate slightly different results from the PyTorch implementation), because this executable file first crops the input image into several tiles, and then processes them separately, finally stitches together.
+
+### Python script
+
+#### Usage of python script
+
+1. You can use X4 model for **arbitrary output size** with the argument `outscale`. The program will further perform cheap resize operation after the Real-ESRGAN output.
+
+```console
+Usage: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile -o outfile [options]...
+
+A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile --outscale 3.5 --face_enhance
+
+  -h                   show this help
+  -i --input           Input image or folder. Default: inputs
+  -o --output          Output folder. Default: results
+  -n --model_name      Model name. Default: RealESRGAN_x4plus
+  -s, --outscale       The final upsampling scale of the image. Default: 4
+  --suffix             Suffix of the restored image. Default: out
+  -t, --tile           Tile size, 0 for no tile during testing. Default: 0
+  --face_enhance       Whether to use GFPGAN to enhance face. Default: False
+  --fp32               Use fp32 precision during inference. Default: fp16 (half precision).
+  --ext                Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto
+```
+
+#### Inference general images
 
 Download pre-trained models: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
 
-Download pretrained models:
-
 ```bash
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights
 ```
 
 Inference!
 
 ```bash
-python inference_realesrgan.py --model_path experiments/pretrained_models/RealESRGAN_x4plus.pth --input inputs --face_enhance
+python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance
 ```
 
 Results are in the `results` folder
 
-## :european_castle: Model Zoo
+#### Inference anime images
 
-- [RealESRGAN-x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
+<p align="center">
-- [RealESRNet-x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth)
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
-- [RealESRGAN-x2plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth)
+</p>
-- [official ESRGAN-x4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth)
 
-## :computer: Training
+Pre-trained models: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)<br>
+ More details and comparisons with [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan) are in [**anime_model.md**](docs/anime_model.md)
 
-A detailed guide can be found in [Training.md](Training.md).
+```bash
+# download model
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
+# inference
+python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
+```
+
+Results are in the `results` folder
+
+---
 
 ## BibTeX
 
-    @Article{wang2021realesrgan,
+    @InProceedings{wang2021realesrgan,
-        title={Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
+        author    = {Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
-        author={Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
+        title     = {Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
-        journal={arXiv:2107.10833},
+        booktitle = {International Conference on Computer Vision Workshops (ICCVW)},
-        year={2021}
+        date      = {2021}
     }
 
-## :e-mail: Contact
+## 📧 Contact
 
 If you have any question, please email `xintao.wang@outlook.com` or `xintaowang@tencent.com`.
+
+<!---------------------------------- Projects that use Real-ESRGAN --------------------------->
+## 🧩 Projects that use Real-ESRGAN
+
+If you develop/use Real-ESRGAN in your projects, welcome to let me know.
+
+- NCNN-Android: [RealSR-NCNN-Android](https://github.com/tumuyan/RealSR-NCNN-Android) by [tumuyan](https://github.com/tumuyan)
+- VapourSynth: [vs-realesrgan](https://github.com/HolyWu/vs-realesrgan) by [HolyWu](https://github.com/HolyWu)
+- NCNN: [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
+
+&nbsp;&nbsp;&nbsp;&nbsp;**GUI**
+
+- [Waifu2x-Extension-GUI](https://github.com/AaronFeng753/Waifu2x-Extension-GUI) by [AaronFeng753](https://github.com/AaronFeng753)
+- [Squirrel-RIFE](https://github.com/Justin62628/Squirrel-RIFE) by [Justin62628](https://github.com/Justin62628)
+- [Real-GUI](https://github.com/scifx/Real-GUI) by [scifx](https://github.com/scifx)
+- [Real-ESRGAN_GUI](https://github.com/net2cn/Real-ESRGAN_GUI) by [net2cn](https://github.com/net2cn)
+- [Real-ESRGAN-EGUI](https://github.com/WGzeyu/Real-ESRGAN-EGUI) by [WGzeyu](https://github.com/WGzeyu)
+- [anime_upscaler](https://github.com/shangar21/anime_upscaler) by [shangar21](https://github.com/shangar21)
+- [Upscayl](https://github.com/upscayl/upscayl) by [Nayam Amarshe](https://github.com/NayamAmarshe) and [TGS963](https://github.com/TGS963)
+
+## 🤗 Acknowledgement
+
+Thanks for all the contributors.
+
+- [AK391](https://github.com/AK391): Integrate RealESRGAN to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/Real-ESRGAN).
+- [Asiimoviet](https://github.com/Asiimoviet): Translate the README.md to Chinese (中文).
+- [2ji3150](https://github.com/2ji3150): Thanks for the [detailed and valuable feedbacks/suggestions](https://github.com/xinntao/Real-ESRGAN/issues/131).
+- [Jared-02](https://github.com/Jared-02): Translate the Training.md to Chinese (中文).

README_CN.md

@@ -0,0 +1,276 @@
+<p align="center">
+  <img src="assets/realesrgan_logo.png" height=120>
+</p>
+
+## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
+
+[![download](https://img.shields.io/github/downloads/xinntao/Real-ESRGAN/total.svg)](https://github.com/xinntao/Real-ESRGAN/releases)
+[![PyPI](https://img.shields.io/pypi/v/realesrgan)](https://pypi.org/project/realesrgan/)
+[![Open issue](https://img.shields.io/github/issues/xinntao/Real-ESRGAN)](https://github.com/xinntao/Real-ESRGAN/issues)
+[![Closed issue](https://img.shields.io/github/issues-closed/xinntao/Real-ESRGAN)](https://github.com/xinntao/Real-ESRGAN/issues)
+[![LICENSE](https://img.shields.io/github/license/xinntao/Real-ESRGAN.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE)
+[![python lint](https://github.com/xinntao/Real-ESRGAN/actions/workflows/pylint.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/pylint.yml)
+[![Publish-pip](https://github.com/xinntao/Real-ESRGAN/actions/workflows/publish-pip.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/publish-pip.yml)
+
+:fire: 更新动漫视频的小模型 **RealESRGAN AnimeVideo-v3**. 更多信息在 [[动漫视频模型介绍](docs/anime_video_model.md)] 和 [[比较](docs/anime_comparisons_CN.md)] 中.
+
+1. Real-ESRGAN的[Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) | Real-ESRGAN**动漫视频** 的[Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing)
+2. **支持Intel/AMD/Nvidia显卡**的绿色版exe文件： [Windows版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [macOS版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip)，详情请移步[这里](#便携版（绿色版）可执行文件)。NCNN的实现在 [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)。
+
+Real-ESRGAN 的目标是开发出**实用的图像/视频修复算法**。<br>
+我们在 ESRGAN 的基础上使用纯合成的数据来进行训练，以使其能被应用于实际的图片修复的场景（顾名思义：Real-ESRGAN）。
+
+:art: Real-ESRGAN 需要，也很欢迎你的贡献，如新功能、模型、bug修复、建议、维护等等。详情可以查看[CONTRIBUTING.md](docs/CONTRIBUTING.md)，所有的贡献者都会被列在[此处](README_CN.md#hugs-感谢)。
+
+:milky_way: 感谢大家提供了很好的反馈。这些反馈会逐步更新在 [这个文档](docs/feedback.md)。
+
+:question: 常见的问题可以在[FAQ.md](docs/FAQ.md)中找到答案。（好吧，现在还是空白的=-=||）
+
+---
+
+如果 Real-ESRGAN 对你有帮助，可以给本项目一个 Star :star: ，或者推荐给你的朋友们，谢谢！:blush: <br/>
+其他推荐的项目：<br/>
+:arrow_forward: [GFPGAN](https://github.com/TencentARC/GFPGAN): 实用的人脸复原算法 <br>
+:arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR): 开源的图像和视频工具箱<br>
+:arrow_forward: [facexlib](https://github.com/xinntao/facexlib): 提供与人脸相关的工具箱<br>
+:arrow_forward: [HandyView](https://github.com/xinntao/HandyView): 基于PyQt5的图片查看器，方便查看以及比较 <br>
+
+---
+
+<!---------------------------------- Updates --------------------------->
+<details>
+<summary>🚩<b>更新</b></summary>
+
+- ✅ 更新动漫视频的小模型 **RealESRGAN AnimeVideo-v3**. 更多信息在 [anime video models](docs/anime_video_model.md) 和 [comparisons](docs/anime_comparisons.md)中.
+- ✅ 添加了针对动漫视频的小模型, 更多信息在 [anime video models](docs/anime_video_model.md) 中.
+- ✅ 添加了ncnn 实现：[Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
+- ✅ 添加了 [*RealESRGAN_x4plus_anime_6B.pth*](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)，对二次元图片进行了优化，并减少了model的大小。详情 以及 与[waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan)的对比请查看[**anime_model.md**](docs/anime_model.md)
+- ✅支持用户在自己的数据上进行微调 (finetune)：[详情](docs/Training.md#Finetune-Real-ESRGAN-on-your-own-dataset)
+- ✅ 支持使用[GFPGAN](https://github.com/TencentARC/GFPGAN)**增强人脸**
+- ✅ 通过[Gradio](https://github.com/gradio-app/gradio)添加到了[Huggingface Spaces](https://huggingface.co/spaces)（一个机器学习应用的在线平台）：[Gradio在线版](https://huggingface.co/spaces/akhaliq/Real-ESRGAN)。感谢[@AK391](https://github.com/AK391)
+- ✅ 支持任意比例的缩放：`--outscale`（实际上使用`LANCZOS4`来更进一步调整输出图像的尺寸）。添加了*RealESRGAN_x2plus.pth*模型
+- ✅ [推断脚本](inference_realesrgan.py)支持: 1) 分块处理**tile**; 2) 带**alpha通道**的图像; 3) **灰色**图像; 4) **16-bit**图像.
+- ✅ 训练代码已经发布，具体做法可查看：[Training.md](docs/Training.md)。
+
+</details>
+
+<!---------------------------------- Projects that use Real-ESRGAN --------------------------->
+<details>
+<summary>🧩<b>使用Real-ESRGAN的项目</b></summary>
+
+&nbsp;&nbsp;&nbsp;&nbsp;👋 如果你开发/使用/集成了Real-ESRGAN, 欢迎联系我添加
+
+- NCNN-Android: [RealSR-NCNN-Android](https://github.com/tumuyan/RealSR-NCNN-Android) by [tumuyan](https://github.com/tumuyan)
+- VapourSynth: [vs-realesrgan](https://github.com/HolyWu/vs-realesrgan) by [HolyWu](https://github.com/HolyWu)
+- NCNN: [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
+
+&nbsp;&nbsp;&nbsp;&nbsp;**易用的图形界面**
+
+- [Waifu2x-Extension-GUI](https://github.com/AaronFeng753/Waifu2x-Extension-GUI) by [AaronFeng753](https://github.com/AaronFeng753)
+- [Squirrel-RIFE](https://github.com/Justin62628/Squirrel-RIFE) by [Justin62628](https://github.com/Justin62628)
+- [Real-GUI](https://github.com/scifx/Real-GUI) by [scifx](https://github.com/scifx)
+- [Real-ESRGAN_GUI](https://github.com/net2cn/Real-ESRGAN_GUI) by [net2cn](https://github.com/net2cn)
+- [Real-ESRGAN-EGUI](https://github.com/WGzeyu/Real-ESRGAN-EGUI) by [WGzeyu](https://github.com/WGzeyu)
+- [anime_upscaler](https://github.com/shangar21/anime_upscaler) by [shangar21](https://github.com/shangar21)
+- [RealESRGAN-GUI](https://github.com/Baiyuetribe/paper2gui/blob/main/Video%20Super%20Resolution/RealESRGAN-GUI.md) by [Baiyuetribe](https://github.com/Baiyuetribe)
+
+</details>
+
+<details>
+<summary>👀<b>Demo视频（B站）</b></summary>
+
+- [大闹天宫片段](https://www.bilibili.com/video/BV1ja41117zb)
+
+</details>
+
+### :book: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
+
+> [[论文](https://arxiv.org/abs/2107.10833)] &emsp; [项目主页] &emsp; [[YouTube 视频](https://www.youtube.com/watch?v=fxHWoDSSvSc)] &emsp; [[B站视频](https://www.bilibili.com/video/BV1H34y1m7sS/)] &emsp; [[Poster](https://xinntao.github.io/projects/RealESRGAN_src/RealESRGAN_poster.pdf)] &emsp; [[PPT](https://docs.google.com/presentation/d/1QtW6Iy8rm8rGLsJ0Ldti6kP-7Qyzy6XL/edit?usp=sharing&ouid=109799856763657548160&rtpof=true&sd=true)]<br>
+> [Xintao Wang](https://xinntao.github.io/), Liangbin Xie, [Chao Dong](https://scholar.google.com.hk/citations?user=OSDCB0UAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>
+> Tencent ARC Lab; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
+
+<p align="center">
+  <img src="assets/teaser.jpg">
+</p>
+
+---
+
+我们提供了一套训练好的模型（*RealESRGAN_x4plus.pth*)，可以进行4倍的超分辨率。<br>
+**现在的 Real-ESRGAN 还是有几率失败的，因为现实生活的降质过程比较复杂。**<br>
+而且，本项目对**人脸以及文字之类**的效果还不是太好，但是我们会持续进行优化的。<br>
+
+Real-ESRGAN 将会被长期支持，我会在空闲的时间中持续维护更新。
+
+这些是未来计划的几个新功能：
+
+- [ ] 优化人脸
+- [ ] 优化文字
+- [x] 优化动画图像
+- [ ] 支持更多的超分辨率比例
+- [ ] 可调节的复原
+
+如果你有好主意或需求，欢迎在 issue 或 discussion 中提出。<br/>
+如果你有一些 Real-ESRGAN 中有问题的照片，你也可以在 issue 或者 discussion 中发出来。我会留意（但是不一定能解决:stuck_out_tongue:）。如果有必要的话，我还会专门开一页来记录那些有待解决的图像。
+
+---
+
+### 便携版（绿色版）可执行文件
+
+你可以下载**支持Intel/AMD/Nvidia显卡**的绿色版exe文件： [Windows版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [macOS版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip)。
+
+绿色版指的是这些exe你可以直接运行（放U盘里拷走都没问题），因为里面已经有所需的文件和模型了。它不需要 CUDA 或者 PyTorch运行环境。<br>
+
+你可以通过下面这个命令来运行（Windows版本的例子，更多信息请查看对应版本的README.md）：
+
+```bash
+./realesrgan-ncnn-vulkan.exe -i 输入图像.jpg -o 输出图像.png -n 模型名字
+```
+
+我们提供了五种模型：
+
+1. realesrgan-x4plus（默认）
+2. reaesrnet-x4plus
+3. realesrgan-x4plus-anime（针对动漫插画图像优化，有更小的体积）
+4. realesr-animevideov3 (针对动漫视频)
+
+你可以通过`-n`参数来使用其他模型，例如`./realesrgan-ncnn-vulkan.exe -i 二次元图片.jpg -o 二刺螈图片.png -n realesrgan-x4plus-anime`
+
+### 可执行文件的用法
+
+1. 更多细节可以参考 [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan#computer-usages).
+2. 注意：可执行文件并没有支持 python 脚本 `inference_realesrgan.py` 中所有的功能，比如 `outscale` 选项) .
+
+```console
+Usage: realesrgan-ncnn-vulkan.exe -i infile -o outfile [options]...
+
+  -h                   show this help
+  -i input-path        input image path (jpg/png/webp) or directory
+  -o output-path       output image path (jpg/png/webp) or directory
+  -s scale             upscale ratio (can be 2, 3, 4. default=4)
+  -t tile-size         tile size (>=32/0=auto, default=0) can be 0,0,0 for multi-gpu
+  -m model-path        folder path to the pre-trained models. default=models
+  -n model-name        model name (default=realesr-animevideov3, can be realesr-animevideov3 | realesrgan-x4plus | realesrgan-x4plus-anime | realesrnet-x4plus)
+  -g gpu-id            gpu device to use (default=auto) can be 0,1,2 for multi-gpu
+  -j load:proc:save    thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu
+  -x                   enable tta mode"
+  -f format            output image format (jpg/png/webp, default=ext/png)
+  -v                   verbose output
+```
+
+由于这些exe文件会把图像分成几个板块，然后来分别进行处理，再合成导出，输出的图像可能会有一点割裂感（而且可能跟PyTorch的输出不太一样）
+
+---
+
+## :wrench: 依赖以及安装
+
+- Python >= 3.7 (推荐使用[Anaconda](https://www.anaconda.com/download/#linux)或[Miniconda](https://docs.conda.io/en/latest/miniconda.html))
+- [PyTorch >= 1.7](https://pytorch.org/)
+
+#### 安装
+
+1. 把项目克隆到本地
+
+    ```bash
+    git clone https://github.com/xinntao/Real-ESRGAN.git
+    cd Real-ESRGAN
+    ```
+
+2. 安装各种依赖
+
+    ```bash
+    # 安装 basicsr - https://github.com/xinntao/BasicSR
+    # 我们使用BasicSR来训练以及推断
+    pip install basicsr
+    # facexlib和gfpgan是用来增强人脸的
+    pip install facexlib
+    pip install gfpgan
+    pip install -r requirements.txt
+    python setup.py develop
+    ```
+
+## :zap: 快速上手
+
+### 普通图片
+
+下载我们训练好的模型: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
+
+```bash
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights
+```
+
+推断!
+
+```bash
+python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance
+```
+
+结果在`results`文件夹
+
+### 动画图片
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+
+训练好的模型: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)<br>
+有关[waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan)的更多信息和对比在[**anime_model.md**](docs/anime_model.md)中。
+
+```bash
+# 下载模型
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
+# 推断
+python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
+```
+
+结果在`results`文件夹
+
+### Python 脚本的用法
+
+1. 虽然你使用了 X4 模型，但是你可以 **输出任意尺寸比例的图片**，只要实用了 `outscale` 参数. 程序会进一步对模型的输出图像进行缩放。
+
+```console
+Usage: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile -o outfile [options]...
+
+A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile --outscale 3.5 --face_enhance
+
+  -h                   show this help
+  -i --input           Input image or folder. Default: inputs
+  -o --output          Output folder. Default: results
+  -n --model_name      Model name. Default: RealESRGAN_x4plus
+  -s, --outscale       The final upsampling scale of the image. Default: 4
+  --suffix             Suffix of the restored image. Default: out
+  -t, --tile           Tile size, 0 for no tile during testing. Default: 0
+  --face_enhance       Whether to use GFPGAN to enhance face. Default: False
+  --fp32               Whether to use half precision during inference. Default: False
+  --ext                Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto
+```
+
+## :european_castle: 模型库
+
+请参见 [docs/model_zoo.md](docs/model_zoo.md)
+
+## :computer: 训练，在你的数据上微调（Fine-tune）
+
+这里有一份详细的指南：[Training.md](docs/Training.md).
+
+## BibTeX 引用
+
+    @Article{wang2021realesrgan,
+        title={Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
+        author={Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
+        journal={arXiv:2107.10833},
+        year={2021}
+    }
+
+## :e-mail: 联系我们
+
+如果你有任何问题，请通过 `xintao.wang@outlook.com` 或 `xintaowang@tencent.com` 联系我们。
+
+## :hugs: 感谢
+
+感谢所有的贡献者大大们~
+
+- [AK391](https://github.com/AK391): 通过[Gradio](https://github.com/gradio-app/gradio)添加到了[Huggingface Spaces](https://huggingface.co/spaces)（一个机器学习应用的在线平台）：[Gradio在线版](https://huggingface.co/spaces/akhaliq/Real-ESRGAN)。
+- [Asiimoviet](https://github.com/Asiimoviet): 把 README.md 文档 翻译成了中文。
+- [2ji3150](https://github.com/2ji3150): 感谢详尽并且富有价值的[反馈、建议](https://github.com/xinntao/Real-ESRGAN/issues/131).
+- [Jared-02](https://github.com/Jared-02): 把 Training.md 文档 翻译成了中文。

Training.md

@@ -1,100 +0,0 @@
-# :computer: How to Train Real-ESRGAN
-
-The training codes have been released. <br>
-Note that the codes have a lot of refactoring. So there may be some bugs/performance drops. Welcome to report bugs/issues.
-
-## Overview
-
-The training has been divided into two stages. These two stages have the same data synthesis process and training pipeline, except for the loss functions. Specifically,
-
-1. We first train Real-ESRNet with L1 loss from the pre-trained model ESRGAN.
-1. We then use the trained Real-ESRNet model as an initialization of the generator, and train the Real-ESRGAN with a combination of L1 loss, perceptual loss and GAN loss.
-
-## Dataset Preparation
-
-We use DF2K (DIV2K and Flickr2K) + OST datasets for our training. Only HR images are required. <br>
-You can download from :
-
-1. DIV2K: http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip
-2. Flickr2K: https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
-3. OST: https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip
-
-For the DF2K dataset, we use a multi-scale strategy, *i.e.*, we downsample HR images to obtain several Ground-Truth images with different scales.
-
-We then crop DF2K images into sub-images for faster IO and processing.
-
-You need to prepare a txt file containing the image paths. The following are some examples in `meta_info_DF2Kmultiscale+OST_sub.txt` (As different users may have different sub-images partitions, this file is not suitable for your purpose and you need to prepare your own txt file):
-
-```txt
-DF2K_HR_sub/000001_s001.png
-DF2K_HR_sub/000001_s002.png
-DF2K_HR_sub/000001_s003.png
-...
-```
-
-## Train Real-ESRNet
-
-1. Download pre-trained model [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) into `experiments/pretrained_models`.
-    ```bash
-    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth -P experiments/pretrained_models
-    ```
-1. Modify the content in the option file `options/train_realesrnet_x4plus.yml` accordingly:
-    ```yml
-    train:
-        name: DF2K+OST
-        type: RealESRGANDataset
-        dataroot_gt: datasets/DF2K  # modify to the root path of your folder
-        meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # modify to your own generate meta info txt
-        io_backend:
-            type: disk
-    ```
-1. If you want to perform validation during training, uncomment those lines and modify accordingly:
-    ```yml
-      # Uncomment these for validation
-      # val:
-      #   name: validation
-      #   type: PairedImageDataset
-      #   dataroot_gt: path_to_gt
-      #   dataroot_lq: path_to_lq
-      #   io_backend:
-      #     type: disk
-
-    ...
-
-      # Uncomment these for validation
-      # validation settings
-      # val:
-      #   val_freq: !!float 5e3
-      #   save_img: True
-
-      #   metrics:
-      #     psnr: # metric name, can be arbitrary
-      #       type: calculate_psnr
-      #       crop_border: 4
-      #       test_y_channel: false
-    ```
-1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
-    ```bash
-    CUDA_VISIBLE_DEVICES=0,1,2,3 \
-    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
-    ```
-1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
-    ```bash
-    CUDA_VISIBLE_DEVICES=0,1,2,3 \
-    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
-    ```
-
-## Train Real-ESRGAN
-
-1. After the training of Real-ESRNet, you now have the file `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth`. If you need to specify the pre-trained path to other files, modify the `pretrain_network_g` value in the option file `train_realesrgan_x4plus.yml`.
-1. Modify the option file `train_realesrgan_x4plus.yml` accordingly. Most modifications are similar to those listed above.
-1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
-    ```bash
-    CUDA_VISIBLE_DEVICES=0,1,2,3 \
-    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
-    ```
-1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
-    ```bash
-    CUDA_VISIBLE_DEVICES=0,1,2,3 \
-    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
-    ```

VERSION

@@ -1 +1 @@
-0.2.2.1
+0.3.0

cog.yaml

@@ -0,0 +1,22 @@
+# This file is used for constructing replicate env
+image: "r8.im/tencentarc/realesrgan"
+
+build:
+  gpu: true
+  python_version: "3.8"
+  system_packages:
+    - "libgl1-mesa-glx"
+    - "libglib2.0-0"
+  python_packages:
+    - "torch==1.7.1"
+    - "torchvision==0.8.2"
+    - "numpy==1.21.1"
+    - "lmdb==1.2.1"
+    - "opencv-python==4.5.3.56"
+    - "PyYAML==5.4.1"
+    - "tqdm==4.62.2"
+    - "yapf==0.31.0"
+    - "basicsr==1.4.2"
+    - "facexlib==0.2.5"
+
+predict: "cog_predict.py:Predictor"

cog_predict.py

@@ -0,0 +1,148 @@
+# flake8: noqa
+# This file is used for deploying replicate models
+# running: cog predict -i img=@inputs/00017_gray.png -i version='General - v3' -i scale=2 -i face_enhance=True -i tile=0
+# push: cog push r8.im/xinntao/realesrgan
+
+import os
+
+os.system('pip install gfpgan')
+os.system('python setup.py develop')
+
+import cv2
+import shutil
+import tempfile
+import torch
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.archs.srvgg_arch import SRVGGNetCompact
+
+from realesrgan.utils import RealESRGANer
+
+try:
+    from cog import BasePredictor, Input, Path
+    from gfpgan import GFPGANer
+except Exception:
+    print('please install cog and realesrgan package')
+
+
+class Predictor(BasePredictor):
+
+    def setup(self):
+        os.makedirs('output', exist_ok=True)
+        # download weights
+        if not os.path.exists('weights/realesr-general-x4v3.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P ./weights'
+            )
+        if not os.path.exists('weights/GFPGANv1.4.pth'):
+            os.system('wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P ./weights')
+        if not os.path.exists('weights/RealESRGAN_x4plus.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P ./weights'
+            )
+        if not os.path.exists('weights/RealESRGAN_x4plus_anime_6B.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P ./weights'
+            )
+        if not os.path.exists('weights/realesr-animevideov3.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P ./weights'
+            )
+
+    def choose_model(self, scale, version, tile=0):
+        half = True if torch.cuda.is_available() else False
+        if version == 'General - RealESRGANplus':
+            model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+            model_path = 'weights/RealESRGAN_x4plus.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'General - v3':
+            model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+            model_path = 'weights/realesr-general-x4v3.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'Anime - anime6B':
+            model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+            model_path = 'weights/RealESRGAN_x4plus_anime_6B.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'AnimeVideo - v3':
+            model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
+            model_path = 'weights/realesr-animevideov3.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+
+        self.face_enhancer = GFPGANer(
+            model_path='weights/GFPGANv1.4.pth',
+            upscale=scale,
+            arch='clean',
+            channel_multiplier=2,
+            bg_upsampler=self.upsampler)
+
+    def predict(
+        self,
+        img: Path = Input(description='Input'),
+        version: str = Input(
+            description='RealESRGAN version. Please see [Readme] below for more descriptions',
+            choices=['General - RealESRGANplus', 'General - v3', 'Anime - anime6B', 'AnimeVideo - v3'],
+            default='General - v3'),
+        scale: float = Input(description='Rescaling factor', default=2),
+        face_enhance: bool = Input(
+            description='Enhance faces with GFPGAN. Note that it does not work for anime images/vidoes', default=False),
+        tile: int = Input(
+            description=
+            'Tile size. Default is 0, that is no tile. When encountering the out-of-GPU-memory issue, please specify it, e.g., 400 or 200',
+            default=0)
+    ) -> Path:
+        if tile <= 100 or tile is None:
+            tile = 0
+        print(f'img: {img}. version: {version}. scale: {scale}. face_enhance: {face_enhance}. tile: {tile}.')
+        try:
+            extension = os.path.splitext(os.path.basename(str(img)))[1]
+            img = cv2.imread(str(img), cv2.IMREAD_UNCHANGED)
+            if len(img.shape) == 3 and img.shape[2] == 4:
+                img_mode = 'RGBA'
+            elif len(img.shape) == 2:
+                img_mode = None
+                img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+            else:
+                img_mode = None
+
+            h, w = img.shape[0:2]
+            if h < 300:
+                img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
+
+            self.choose_model(scale, version, tile)
+
+            try:
+                if face_enhance:
+                    _, _, output = self.face_enhancer.enhance(
+                        img, has_aligned=False, only_center_face=False, paste_back=True)
+                else:
+                    output, _ = self.upsampler.enhance(img, outscale=scale)
+            except RuntimeError as error:
+                print('Error', error)
+                print('If you encounter CUDA out of memory, try to set "tile" to a smaller size, e.g., 400.')
+
+            if img_mode == 'RGBA':  # RGBA images should be saved in png format
+                extension = 'png'
+            # save_path = f'output/out.{extension}'
+            # cv2.imwrite(save_path, output)
+            out_path = Path(tempfile.mkdtemp()) / f'out.{extension}'
+            cv2.imwrite(str(out_path), output)
+        except Exception as error:
+            print('global exception: ', error)
+        finally:
+            clean_folder('output')
+        return out_path
+
+
+def clean_folder(folder):
+    for filename in os.listdir(folder):
+        file_path = os.path.join(folder, filename)
+        try:
+            if os.path.isfile(file_path) or os.path.islink(file_path):
+                os.unlink(file_path)
+            elif os.path.isdir(file_path):
+                shutil.rmtree(file_path)
+        except Exception as e:
+            print(f'Failed to delete {file_path}. Reason: {e}')

docs/CONTRIBUTING.md

@@ -0,0 +1,44 @@
+# Contributing to Real-ESRGAN
+
+:art: Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, *etc*. See [CONTRIBUTING.md](docs/CONTRIBUTING.md). All contributors are list [here](README.md#hugs-acknowledgement).
+
+We like open-source and want to develop practical algorithms for general image restoration. However, individual strength is limited. So, any kinds of contributions are welcome, such as:
+
+- New features
+- New models (your fine-tuned models)
+- Bug fixes
+- Typo fixes
+- Suggestions
+- Maintenance
+- Documents
+- *etc*
+
+## Workflow
+
+1. Fork and pull the latest Real-ESRGAN repository
+1. Checkout a new branch (do not use master branch for PRs)
+1. Commit your changes
+1. Create a PR
+
+**Note**:
+
+1. Please check the code style and linting
+    1. The style configuration is specified in [setup.cfg](setup.cfg)
+    1. If you use VSCode, the settings are configured in [.vscode/settings.json](.vscode/settings.json)
+1. Strongly recommend using `pre-commit hook`. It will check your code style and linting before your commit.
+    1. In the root path of project folder, run `pre-commit install`
+    1. The pre-commit configuration is listed in [.pre-commit-config.yaml](.pre-commit-config.yaml)
+1. Better to [open a discussion](https://github.com/xinntao/Real-ESRGAN/discussions) before large changes.
+    1. Welcome to discuss :sunglasses:. I will try my best to join the discussion.
+
+## TODO List
+
+:zero: The most straightforward way of improving model performance is to fine-tune on some specific datasets.
+
+Here are some TODOs:
+
+- [ ] optimize for human faces
+- [ ] optimize for texts
+- [ ] support controllable restoration strength
+
+:one: There are also [several issues](https://github.com/xinntao/Real-ESRGAN/issues) that require helpers to improve. If you can help, please let me know :smile:

docs/FAQ.md

@@ -0,0 +1,10 @@
+# FAQ
+
+1. **Q: How to select models?**<br>
+A: Please refer to [docs/model_zoo.md](docs/model_zoo.md)
+
+1. **Q: Can `face_enhance` be used for anime images/animation videos?**<br>
+A: No, it can only be used for real faces. It is recommended not to use this option for anime images/animation videos to save GPU memory.
+
+1. **Q: Error "slow_conv2d_cpu" not implemented for 'Half'**<br>
+A: In order to save GPU memory consumption and speed up inference, Real-ESRGAN uses half precision (fp16) during inference by default. However, some operators for half inference are not implemented in CPU mode. You need to add **`--fp32` option** for the commands. For example, `python inference_realesrgan.py -n RealESRGAN_x4plus.pth -i inputs --fp32`.

docs/Training.md

@@ -0,0 +1,271 @@
+# :computer: How to Train/Finetune Real-ESRGAN
+
+- [Train Real-ESRGAN](#train-real-esrgan)
+  - [Overview](#overview)
+  - [Dataset Preparation](#dataset-preparation)
+  - [Train Real-ESRNet](#Train-Real-ESRNet)
+  - [Train Real-ESRGAN](#Train-Real-ESRGAN)
+- [Finetune Real-ESRGAN on your own dataset](#Finetune-Real-ESRGAN-on-your-own-dataset)
+  - [Generate degraded images on the fly](#Generate-degraded-images-on-the-fly)
+  - [Use paired training data](#use-your-own-paired-data)
+
+[English](Training.md) **|** [简体中文](Training_CN.md)
+
+## Train Real-ESRGAN
+
+### Overview
+
+The training has been divided into two stages. These two stages have the same data synthesis process and training pipeline, except for the loss functions. Specifically,
+
+1. We first train Real-ESRNet with L1 loss from the pre-trained model ESRGAN.
+1. We then use the trained Real-ESRNet model as an initialization of the generator, and train the Real-ESRGAN with a combination of L1 loss, perceptual loss and GAN loss.
+
+### Dataset Preparation
+
+We use DF2K (DIV2K and Flickr2K) + OST datasets for our training. Only HR images are required. <br>
+You can download from :
+
+1. DIV2K: http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip
+2. Flickr2K: https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
+3. OST: https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip
+
+Here are steps for data preparation.
+
+#### Step 1: [Optional] Generate multi-scale images
+
+For the DF2K dataset, we use a multi-scale strategy, *i.e.*, we downsample HR images to obtain several Ground-Truth images with different scales. <br>
+You can use the [scripts/generate_multiscale_DF2K.py](scripts/generate_multiscale_DF2K.py) script to generate multi-scale images. <br>
+Note that this step can be omitted if you just want to have a fast try.
+
+```bash
+python scripts/generate_multiscale_DF2K.py --input datasets/DF2K/DF2K_HR --output datasets/DF2K/DF2K_multiscale
+```
+
+#### Step 2: [Optional] Crop to sub-images
+
+We then crop DF2K images into sub-images for faster IO and processing.<br>
+This step is optional if your IO is enough or your disk space is limited.
+
+You can use the [scripts/extract_subimages.py](scripts/extract_subimages.py) script. Here is the example:
+
+```bash
+ python scripts/extract_subimages.py --input datasets/DF2K/DF2K_multiscale --output datasets/DF2K/DF2K_multiscale_sub --crop_size 400 --step 200
+```
+
+#### Step 3: Prepare a txt for meta information
+
+You need to prepare a txt file containing the image paths. The following are some examples in `meta_info_DF2Kmultiscale+OST_sub.txt` (As different users may have different sub-images partitions, this file is not suitable for your purpose and you need to prepare your own txt file):
+
+```txt
+DF2K_HR_sub/000001_s001.png
+DF2K_HR_sub/000001_s002.png
+DF2K_HR_sub/000001_s003.png
+...
+```
+
+You can use the [scripts/generate_meta_info.py](scripts/generate_meta_info.py) script to generate the txt file. <br>
+You can merge several folders into one meta_info txt. Here is the example:
+
+```bash
+ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR datasets/DF2K/DF2K_multiscale --root datasets/DF2K datasets/DF2K --meta_info datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt
+```
+
+### Train Real-ESRNet
+
+1. Download pre-trained model [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) into `experiments/pretrained_models`.
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth -P experiments/pretrained_models
+    ```
+1. Modify the content in the option file `options/train_realesrnet_x4plus.yml` accordingly:
+    ```yml
+    train:
+        name: DF2K+OST
+        type: RealESRGANDataset
+        dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+        meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # modify to your own generate meta info txt
+        io_backend:
+            type: disk
+    ```
+1. If you want to perform validation during training, uncomment those lines and modify accordingly:
+    ```yml
+      # Uncomment these for validation
+      # val:
+      #   name: validation
+      #   type: PairedImageDataset
+      #   dataroot_gt: path_to_gt
+      #   dataroot_lq: path_to_lq
+      #   io_backend:
+      #     type: disk
+
+    ...
+
+      # Uncomment these for validation
+      # validation settings
+      # val:
+      #   val_freq: !!float 5e3
+      #   save_img: True
+
+      #   metrics:
+      #     psnr: # metric name, can be arbitrary
+      #       type: calculate_psnr
+      #       crop_border: 4
+      #       test_y_channel: false
+    ```
+1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
+    ```
+
+    Train with **a single GPU** in the *debug* mode:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --debug
+    ```
+1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    Train with **a single GPU**:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
+    ```
+
+### Train Real-ESRGAN
+
+1. After the training of Real-ESRNet, you now have the file `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth`. If you need to specify the pre-trained path to other files, modify the `pretrain_network_g` value in the option file `train_realesrgan_x4plus.yml`.
+1. Modify the option file `train_realesrgan_x4plus.yml` accordingly. Most modifications are similar to those listed above.
+1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
+    ```
+
+    Train with **a single GPU** in the *debug* mode:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --debug
+    ```
+1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    Train with **a single GPU**:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --auto_resume
+    ```
+
+## Finetune Real-ESRGAN on your own dataset
+
+You can finetune Real-ESRGAN on your own dataset. Typically, the fine-tuning process can be divided into two cases:
+
+1. [Generate degraded images on the fly](#Generate-degraded-images-on-the-fly)
+1. [Use your own **paired** data](#Use-paired-training-data)
+
+### Generate degraded images on the fly
+
+Only high-resolution images are required. The low-quality images are generated with the degradation process described in Real-ESRGAN during training.
+
+**1. Prepare dataset**
+
+See [this section](#dataset-preparation) for more details.
+
+**2. Download pre-trained models**
+
+Download pre-trained models into `experiments/pretrained_models`.
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. Finetune**
+
+Modify [options/finetune_realesrgan_x4plus.yml](options/finetune_realesrgan_x4plus.yml) accordingly, especially the `datasets` part:
+
+```yml
+train:
+    name: DF2K+OST
+    type: RealESRGANDataset
+    dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+    meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # modify to your own generate meta info txt
+    io_backend:
+        type: disk
+```
+
+We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+```
+
+Finetune with **a single GPU**:
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --auto_resume
+```
+
+### Use your own paired data
+
+You can also finetune RealESRGAN with your own paired data. It is more similar to fine-tuning ESRGAN.
+
+**1. Prepare dataset**
+
+Assume that you already have two folders:
+
+- **gt folder** (Ground-truth, high-resolution images): *datasets/DF2K/DIV2K_train_HR_sub*
+- **lq folder** (Low quality, low-resolution images): *datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub*
+
+Then, you can prepare the meta_info txt file using the script [scripts/generate_meta_info_pairdata.py](scripts/generate_meta_info_pairdata.py):
+
+```bash
+python scripts/generate_meta_info_pairdata.py --input datasets/DF2K/DIV2K_train_HR_sub datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub --meta_info datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
+```
+
+**2. Download pre-trained models**
+
+Download pre-trained models into `experiments/pretrained_models`.
+
+- *RealESRGAN_x4plus.pth*
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. Finetune**
+
+Modify [options/finetune_realesrgan_x4plus_pairdata.yml](options/finetune_realesrgan_x4plus_pairdata.yml) accordingly, especially the `datasets` part:
+
+```yml
+train:
+    name: DIV2K
+    type: RealESRGANPairedDataset
+    dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+    dataroot_lq: datasets/DF2K  # modify to the root path of your folder
+    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt  # modify to your own generate meta info txt
+    io_backend:
+        type: disk
+```
+
+We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume
+```
+
+Finetune with **a single GPU**:
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --auto_resume
+```

docs/Training_CN.md

@@ -0,0 +1,271 @@
+# :computer: 如何训练/微调 Real-ESRGAN
+
+- [训练 Real-ESRGAN](#训练-real-esrgan)
+  - [概述](#概述)
+  - [准备数据集](#准备数据集)
+  - [训练 Real-ESRNet 模型](#训练-real-esrnet-模型)
+  - [训练 Real-ESRGAN 模型](#训练-real-esrgan-模型)
+- [用自己的数据集微调 Real-ESRGAN](#用自己的数据集微调-real-esrgan)
+  - [动态生成降级图像](#动态生成降级图像)
+  - [使用已配对的数据](#使用已配对的数据)
+
+[English](Training.md) **|** [简体中文](Training_CN.md)
+
+## 训练 Real-ESRGAN
+
+### 概述
+
+训练分为两个步骤。除了 loss 函数外，这两个步骤拥有相同数据合成以及训练的一条龙流程。具体点说：
+
+1. 首先使用 L1 loss 训练 Real-ESRNet 模型，其中 L1 loss 来自预先训练的 ESRGAN 模型。
+
+2. 然后我们将 Real-ESRNet 模型作为生成器初始化，结合L1 loss、感知 loss、GAN loss 三者的参数对 Real-ESRGAN 进行训练。
+
+### 准备数据集
+
+我们使用 DF2K ( DIV2K 和 Flickr2K ) + OST 数据集进行训练。只需要HR图像！<br>
+下面是网站链接:
+1. DIV2K: http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip
+2. Flickr2K: https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
+3. OST: https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip
+
+以下是数据的准备步骤。
+
+#### 第1步：【可选】生成多尺寸图片
+
+针对 DF2K 数据集，我们使用多尺寸缩放策略，*换言之*，我们对 HR 图像进行下采样，就能获得多尺寸的标准参考（Ground-Truth）图像。 <br>
+您可以使用这个 [scripts/generate_multiscale_DF2K.py](scripts/generate_multiscale_DF2K.py) 脚本快速生成多尺寸的图像。<br>
+注意：如果您只想简单试试，那么可以跳过此步骤。
+
+```bash
+python scripts/generate_multiscale_DF2K.py --input datasets/DF2K/DF2K_HR --output datasets/DF2K/DF2K_multiscale
+```
+
+#### 第2步：【可选】裁切为子图像
+
+我们可以将 DF2K 图像裁切为子图像，以加快 IO 和处理速度。<br>
+如果你的 IO 够好或储存空间有限，那么此步骤是可选的。<br>
+
+您可以使用脚本 [scripts/extract_subimages.py](scripts/extract_subimages.py)。这是使用示例:
+
+```bash
+ python scripts/extract_subimages.py --input datasets/DF2K/DF2K_multiscale --output datasets/DF2K/DF2K_multiscale_sub --crop_size 400 --step 200
+```
+
+#### 第3步：准备元信息 txt
+
+您需要准备一个包含图像路径的 txt 文件。下面是 `meta_info_DF2Kmultiscale+OST_sub.txt` 中的部分展示（由于各个用户可能有截然不同的子图像划分，这个文件不适合你的需求，你得准备自己的 txt 文件)：
+
+```txt
+DF2K_HR_sub/000001_s001.png
+DF2K_HR_sub/000001_s002.png
+DF2K_HR_sub/000001_s003.png
+...
+```
+
+你可以使用该脚本 [scripts/generate_meta_info.py](scripts/generate_meta_info.py) 生成包含图像路径的 txt 文件。<br>
+你还可以合并多个文件夹的图像路径到一个元信息（meta_info）txt。这是使用示例:
+
+```bash
+ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR, datasets/DF2K/DF2K_multiscale --root datasets/DF2K, datasets/DF2K --meta_info datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt
+```
+
+### 训练 Real-ESRNet 模型
+
+1. 下载预先训练的模型 [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth)，放到 `experiments/pretrained_models`目录下。
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth -P experiments/pretrained_models
+    ```
+2. 相应地修改选项文件 `options/train_realesrnet_x4plus.yml` 中的内容：
+    ```yml
+    train:
+        name: DF2K+OST
+        type: RealESRGANDataset
+        dataroot_gt: datasets/DF2K  # 修改为你的数据集文件夹根目录
+        meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # 修改为你自己生成的元信息txt
+        io_backend:
+            type: disk
+    ```
+3. 如果你想在训练过程中执行验证，就取消注释这些内容并进行相应的修改：
+    ```yml
+      # 取消注释这些以进行验证
+      # val:
+      #   name: validation
+      #   type: PairedImageDataset
+      #   dataroot_gt: path_to_gt
+      #   dataroot_lq: path_to_lq
+      #   io_backend:
+      #     type: disk
+
+    ...
+
+      # 取消注释这些以进行验证
+      # 验证设置
+      # val:
+      #   val_freq: !!float 5e3
+      #   save_img: True
+
+      #   metrics:
+      #     psnr: # 指标名称，可以是任意的
+      #       type: calculate_psnr
+      #       crop_border: 4
+      #       test_y_channel: false
+    ```
+4. 正式训练之前，你可以用 `--debug` 模式检查是否正常运行。我们用了4个GPU进行训练：
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
+    ```
+
+    用 **1个GPU** 训练的 debug 模式示例:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --debug
+    ```
+5. 正式训练开始。我们用了4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    用 **1个GPU** 训练：
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
+    ```
+
+### 训练 Real-ESRGAN 模型
+
+1. 训练 Real-ESRNet 模型后，您得到了这个 `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth` 文件。如果需要指定预训练路径到其他文件，请修改选项文件 `train_realesrgan_x4plus.yml` 中 `pretrain_network_g` 的值。
+1. 修改选项文件 `train_realesrgan_x4plus.yml` 的内容。大多数修改与上节提到的类似。
+1. 正式训练之前，你可以以 `--debug` 模式检查是否正常运行。我们使用了4个GPU进行训练：
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
+    ```
+
+    用 **1个GPU** 训练的 debug 模式示例:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --debug
+    ```
+1. 正式训练开始。我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    用 **1个GPU** 训练：
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --auto_resume
+    ```
+
+## 用自己的数据集微调 Real-ESRGAN
+
+你可以用自己的数据集微调 Real-ESRGAN。一般地，微调（Fine-Tune）程序可以分为两种类型:
+
+1. [动态生成降级图像](#动态生成降级图像)
+2. [使用**已配对**的数据](#使用已配对的数据)
+
+### 动态生成降级图像
+
+只需要高分辨率图像。在训练过程中，使用 Real-ESRGAN 描述的降级模型生成低质量图像。
+
+**1. 准备数据集**
+
+完整信息请参见[本节](#准备数据集)。
+
+**2. 下载预训练模型**
+
+下载预先训练的模型到 `experiments/pretrained_models` 目录下。
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. 微调**
+
+修改选项文件 [options/finetune_realesrgan_x4plus.yml](options/finetune_realesrgan_x4plus.yml) ，特别是 `datasets` 部分：
+
+```yml
+train:
+    name: DF2K+OST
+    type: RealESRGANDataset
+    dataroot_gt: datasets/DF2K   # 修改为你的数据集文件夹根目录
+    meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # 修改为你自己生成的元信息txt
+    io_backend:
+        type: disk
+```
+
+我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+```
+
+用 **1个GPU** 训练：
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --auto_resume
+```
+
+### 使用已配对的数据
+
+你还可以用自己已经配对的数据微调 RealESRGAN。这个过程更类似于微调 ESRGAN。
+
+**1. 准备数据集**
+
+假设你已经有两个文件夹（folder）:
+
+- **gt folder**（标准参考，高分辨率图像）：*datasets/DF2K/DIV2K_train_HR_sub*
+- **lq folder**（低质量，低分辨率图像）：*datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub*
+
+然后，您可以使用脚本 [scripts/generate_meta_info_pairdata.py](scripts/generate_meta_info_pairdata.py) 生成元信息（meta_info）txt 文件。
+
+```bash
+python scripts/generate_meta_info_pairdata.py --input datasets/DF2K/DIV2K_train_HR_sub datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub --meta_info datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
+```
+
+**2. 下载预训练模型**
+
+下载预先训练的模型到 `experiments/pretrained_models` 目录下。
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. 微调**
+
+修改选项文件 [options/finetune_realesrgan_x4plus_pairdata.yml](options/finetune_realesrgan_x4plus_pairdata.yml) ，特别是 `datasets` 部分：
+
+```yml
+train:
+    name: DIV2K
+    type: RealESRGANPairedDataset
+    dataroot_gt: datasets/DF2K  # 修改为你的 gt folder 文件夹根目录
+    dataroot_lq: datasets/DF2K  # 修改为你的 lq folder 文件夹根目录
+    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt  # 修改为你自己生成的元信息txt
+    io_backend:
+        type: disk
+```
+
+我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume
+```
+
+用 **1个GPU** 训练：
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --auto_resume
+```

docs/anime_comparisons.md

@@ -0,0 +1,66 @@
+# Comparisons among different anime models
+
+[English](anime_comparisons.md) **|** [简体中文](anime_comparisons_CN.md)
+
+## Update News
+
+- 2022/04/24: Release **AnimeVideo-v3**. We have made the following improvements:
+  - **better naturalness**
+  - **Fewer artifacts**
+  - **more faithful to the original colors**
+  - **better texture restoration**
+  - **better background restoration**
+
+## Comparisons
+
+We have compared our RealESRGAN-AnimeVideo-v3 with the following methods.
+Our RealESRGAN-AnimeVideo-v3 can achieve better results with faster inference speed.
+
+- [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan) with the hyperparameters: `tile=0`, `noiselevel=2`
+- [Real-CUGAN](https://github.com/bilibili/ailab/tree/main/Real-CUGAN): we use the [20220227](https://github.com/bilibili/ailab/releases/tag/Real-CUGAN-add-faster-low-memory-mode) version, the hyperparameters are: `cache_mode=0`, `tile=0`, `alpha=1`.
+- our RealESRGAN-AnimeVideo-v3
+
+## Results
+
+You may need to **zoom in** for comparing details, or **click the image** to see in the full size. Please note that the images
+in the table below are the resized and cropped patches from the original images, you can download the original inputs and outputs from [Google Drive](https://drive.google.com/drive/folders/1bc_Hje1Nqop9NDkUvci2VACSjL7HZMRp?usp=sharing) .
+
+**More natural results, better background restoration**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![157083983-bec52c67-9a5e-4eed-afef-01fe6cd2af85_patch](https://user-images.githubusercontent.com/11482921/164452769-5d8cb4f8-1708-42d2-b941-f44a6f136feb.png) | ![](https://user-images.githubusercontent.com/11482921/164452767-c825cdec-f721-4ff1-aef1-fec41f146c4c.png) | ![](https://user-images.githubusercontent.com/11482921/164452755-3be50895-e3d4-432d-a7b9-9085c2a8e771.png) | ![](https://user-images.githubusercontent.com/11482921/164452771-be300656-379a-4323-a755-df8025a8c451.png) |
+|![a0010_patch](https://user-images.githubusercontent.com/11482921/164454047-22eeb493-3fa9-4142-9fc2-6f2a1c074cd5.png) | ![](https://user-images.githubusercontent.com/11482921/164454046-d5e79f8f-00a0-4b55-bc39-295d0d69747a.png) | ![](https://user-images.githubusercontent.com/11482921/164454040-87886b11-9d08-48bd-862f-0d4aed72eb19.png) | ![](https://user-images.githubusercontent.com/11482921/164454055-73dc9f02-286e-4d5c-8f70-c13742e08f42.png) |
+|![00000044_patch](https://user-images.githubusercontent.com/11482921/164451232-bacf64fc-e55a-44db-afbb-6b31ab0f8973.png) | ![](https://user-images.githubusercontent.com/11482921/164451318-f309b61a-75b8-4b74-b5f3-595725f1cf0b.png) | ![](https://user-images.githubusercontent.com/11482921/164451348-994f8a35-adbe-4a4b-9c61-feaa294af06a.png) | ![](https://user-images.githubusercontent.com/11482921/164451361-9b7d376e-6f75-4648-b752-542b44845d1c.png) |
+
+**Fewer artifacts, better detailed textures**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![00000053_patch](https://user-images.githubusercontent.com/11482921/164448411-148a7e5c-cfcd-4504-8bc7-e318eb883bb6.png) | ![](https://user-images.githubusercontent.com/11482921/164448633-dfc15224-b6d2-4403-a3c9-4bb819979364.png) | ![](https://user-images.githubusercontent.com/11482921/164448771-0d359509-5293-4d4c-8e3c-86a2a314ea88.png) | ![](https://user-images.githubusercontent.com/11482921/164448848-1a4ff99e-075b-4458-9db7-2c89e8160aa0.png) |
+|![Disney_v4_22_018514_s2_patch](https://user-images.githubusercontent.com/11482921/164451898-83311cdf-bd3e-450f-b9f6-34d7fea3ab79.png) | ![](https://user-images.githubusercontent.com/11482921/164451894-6c56521c-6561-40d6-a3a5-8dde2c167b8a.png) | ![](https://user-images.githubusercontent.com/11482921/164451888-af9b47e3-39dc-4f3e-b0d7-d372d8191e2a.png) | ![](https://user-images.githubusercontent.com/11482921/164451901-31ca4dd4-9847-4baa-8cde-ad50f4053dcf.png) |
+|![Japan_v2_0_007261_s2_patch](https://user-images.githubusercontent.com/11482921/164454578-73c77392-77de-49c5-b03c-c36631723192.png) | ![](https://user-images.githubusercontent.com/11482921/164454574-b1ede5f0-4520-4eaa-8f59-086751a34e62.png) | ![](https://user-images.githubusercontent.com/11482921/164454567-4cb3fdd8-6a2d-4016-85b2-a305a8ff80e4.png) | ![](https://user-images.githubusercontent.com/11482921/164454583-7f243f20-eca3-4500-ac43-eb058a4a101a.png) |
+|![huluxiongdi_2_patch](https://user-images.githubusercontent.com/11482921/164453482-0726c842-337e-40ec-bf6c-f902ee956a8b.png) | ![](https://user-images.githubusercontent.com/11482921/164453480-71d5e091-5bfa-4c77-9c57-4e37f66ca0a3.png) | ![](https://user-images.githubusercontent.com/11482921/164453468-c295d3c9-3661-45f0-9ecd-406a1877f76e.png) | ![](https://user-images.githubusercontent.com/11482921/164453486-3091887c-587c-450e-b6fe-905cb518d57e.png) |
+
+**Other better results**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![Japan_v2_1_128525_s1_patch](https://user-images.githubusercontent.com/11482921/164454933-67697f7c-b6ef-47dc-bfca-822a78af8acf.png) | ![](https://user-images.githubusercontent.com/11482921/164454931-9450de7c-f0b3-4638-9c1e-0668e0c41ef0.png) | ![](https://user-images.githubusercontent.com/11482921/164454926-ed746976-786d-41c5-8a83-7693cd774c3a.png) | ![](https://user-images.githubusercontent.com/11482921/164454936-8abdf0f0-fb30-40eb-8281-3b46c0bcb9ae.png) |
+|![tianshuqitan_2_patch](https://user-images.githubusercontent.com/11482921/164456948-807c1476-90b6-4507-81da-cb986d01600c.png) | ![](https://user-images.githubusercontent.com/11482921/164456943-25e89de9-d7e5-4f61-a2e1-96786af6ae9e.png) | ![](https://user-images.githubusercontent.com/11482921/164456954-b468c447-59f5-4594-9693-3683e44ba3e6.png) | ![](https://user-images.githubusercontent.com/11482921/164456957-640f910c-3b04-407c-ac20-044d72e19735.png) |
+|![00000051_patch](https://user-images.githubusercontent.com/11482921/164456044-e9a6b3fa-b24e-4eb7-acf9-1f7746551b1e.png) ![00000051_patch](https://user-images.githubusercontent.com/11482921/164456421-b67245b0-767d-4250-9105-80bbe507ecfc.png) | ![](https://user-images.githubusercontent.com/11482921/164456040-85763cf2-cb28-4ba3-abb6-1dbb48c55713.png) ![](https://user-images.githubusercontent.com/11482921/164456419-59cf342e-bc1e-4044-868c-e1090abad313.png) | ![](https://user-images.githubusercontent.com/11482921/164456031-4244bb7b-8649-4e01-86f4-40c2099c5afd.png) ![](https://user-images.githubusercontent.com/11482921/164456411-b6afcbe9-c054-448d-a6df-96d3ba3047f8.png) | ![](https://user-images.githubusercontent.com/11482921/164456035-12e270be-fd52-46d4-b18a-3d3b680731fe.png) ![](https://user-images.githubusercontent.com/11482921/164456417-dcaa8b62-f497-427d-b2d2-f390f1200fb9.png) |
+|![00000099_patch](https://user-images.githubusercontent.com/11482921/164455312-6411b6e1-5823-4131-a4b0-a6be8a9ae89f.png) | ![](https://user-images.githubusercontent.com/11482921/164455310-f2b99646-3a22-47a4-805b-dc451ac86ddb.png) | ![](https://user-images.githubusercontent.com/11482921/164455294-35471b42-2826-4451-b7ec-6de01344954c.png) | ![](https://user-images.githubusercontent.com/11482921/164455305-fa4c9758-564a-4081-8b4e-f11057a0404d.png) |
+|![00000016_patch](https://user-images.githubusercontent.com/11482921/164455672-447353c9-2da2-4fcb-ba4a-7dd6b94c19c1.png) | ![](https://user-images.githubusercontent.com/11482921/164455669-df384631-baaa-42f8-9150-40f658471558.png) | ![](https://user-images.githubusercontent.com/11482921/164455657-68006bf0-138d-4981-aaca-8aa927d2f78a.png) | ![](https://user-images.githubusercontent.com/11482921/164455664-0342b93e-a62a-4b36-a90e-7118f3f1e45d.png) |
+
+## Inference Speed
+
+### PyTorch
+
+Note that we only report the **model** time, and ignore the IO time.
+
+| GPU | Input Resolution | waifu2x | Real-CUGAN | RealESRGAN-AnimeVideo-v3
+| :---: | :---:         |  :---:        |     :---:      |  :---:      |
+| V100 | 1921 x 1080 | - | 3.4 fps | **10.0** fps |
+| V100 | 1280 x 720 | - | 7.2 fps | **22.6** fps |
+| V100 | 640 x 480 | - | 24.4 fps | **65.9** fps |
+
+### ncnn
+
+- [ ] TODO

docs/anime_comparisons_CN.md

@@ -0,0 +1,68 @@
+# 动漫视频模型比较
+
+[English](anime_comparisons.md) **|** [简体中文](anime_comparisons_CN.md)
+
+## 更新
+
+- 2022/04/24: 发布 **AnimeVideo-v3**. 主要做了以下更新：
+  - **更自然**
+  - **更少瑕疵**
+  - **颜色保持得更好**
+  - **更好的纹理恢复**
+  - **虚化背景处理**
+
+## 比较
+
+我们将 RealESRGAN-AnimeVideo-v3 与以下方法进行了比较。我们的 RealESRGAN-AnimeVideo-v3 可以以更快的推理速度获得更好的结果。
+
+- [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan). 超参数: `tile=0`, `noiselevel=2`
+- [Real-CUGAN](https://github.com/bilibili/ailab/tree/main/Real-CUGAN): 我们使用了[20220227](https://github.com/bilibili/ailab/releases/tag/Real-CUGAN-add-faster-low-memory-mode)版本, 超参: `cache_mode=0`, `tile=0`, `alpha=1`.
+- 我们的 RealESRGAN-AnimeVideo-v3
+
+## 结果
+
+您可能需要**放大**以比较详细信息, 或者**单击图像**以查看完整尺寸。 请注意下面表格的图片是从原图里裁剪patch并且resize后的结果，您可以从
+[Google Drive](https://drive.google.com/drive/folders/1bc_Hje1Nqop9NDkUvci2VACSjL7HZMRp?usp=sharing) 里下载原始的输入和输出。
+
+**更自然的结果，更好的虚化背景恢复**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![157083983-bec52c67-9a5e-4eed-afef-01fe6cd2af85_patch](https://user-images.githubusercontent.com/11482921/164452769-5d8cb4f8-1708-42d2-b941-f44a6f136feb.png) | ![](https://user-images.githubusercontent.com/11482921/164452767-c825cdec-f721-4ff1-aef1-fec41f146c4c.png) | ![](https://user-images.githubusercontent.com/11482921/164452755-3be50895-e3d4-432d-a7b9-9085c2a8e771.png) | ![](https://user-images.githubusercontent.com/11482921/164452771-be300656-379a-4323-a755-df8025a8c451.png) |
+|![a0010_patch](https://user-images.githubusercontent.com/11482921/164454047-22eeb493-3fa9-4142-9fc2-6f2a1c074cd5.png) | ![](https://user-images.githubusercontent.com/11482921/164454046-d5e79f8f-00a0-4b55-bc39-295d0d69747a.png) | ![](https://user-images.githubusercontent.com/11482921/164454040-87886b11-9d08-48bd-862f-0d4aed72eb19.png) | ![](https://user-images.githubusercontent.com/11482921/164454055-73dc9f02-286e-4d5c-8f70-c13742e08f42.png) |
+|![00000044_patch](https://user-images.githubusercontent.com/11482921/164451232-bacf64fc-e55a-44db-afbb-6b31ab0f8973.png) | ![](https://user-images.githubusercontent.com/11482921/164451318-f309b61a-75b8-4b74-b5f3-595725f1cf0b.png) | ![](https://user-images.githubusercontent.com/11482921/164451348-994f8a35-adbe-4a4b-9c61-feaa294af06a.png) | ![](https://user-images.githubusercontent.com/11482921/164451361-9b7d376e-6f75-4648-b752-542b44845d1c.png) |
+
+**更少瑕疵，更好的细节纹理**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![00000053_patch](https://user-images.githubusercontent.com/11482921/164448411-148a7e5c-cfcd-4504-8bc7-e318eb883bb6.png) | ![](https://user-images.githubusercontent.com/11482921/164448633-dfc15224-b6d2-4403-a3c9-4bb819979364.png) | ![](https://user-images.githubusercontent.com/11482921/164448771-0d359509-5293-4d4c-8e3c-86a2a314ea88.png) | ![](https://user-images.githubusercontent.com/11482921/164448848-1a4ff99e-075b-4458-9db7-2c89e8160aa0.png) |
+|![Disney_v4_22_018514_s2_patch](https://user-images.githubusercontent.com/11482921/164451898-83311cdf-bd3e-450f-b9f6-34d7fea3ab79.png) | ![](https://user-images.githubusercontent.com/11482921/164451894-6c56521c-6561-40d6-a3a5-8dde2c167b8a.png) | ![](https://user-images.githubusercontent.com/11482921/164451888-af9b47e3-39dc-4f3e-b0d7-d372d8191e2a.png) | ![](https://user-images.githubusercontent.com/11482921/164451901-31ca4dd4-9847-4baa-8cde-ad50f4053dcf.png) |
+|![Japan_v2_0_007261_s2_patch](https://user-images.githubusercontent.com/11482921/164454578-73c77392-77de-49c5-b03c-c36631723192.png) | ![](https://user-images.githubusercontent.com/11482921/164454574-b1ede5f0-4520-4eaa-8f59-086751a34e62.png) | ![](https://user-images.githubusercontent.com/11482921/164454567-4cb3fdd8-6a2d-4016-85b2-a305a8ff80e4.png) | ![](https://user-images.githubusercontent.com/11482921/164454583-7f243f20-eca3-4500-ac43-eb058a4a101a.png) |
+|![huluxiongdi_2_patch](https://user-images.githubusercontent.com/11482921/164453482-0726c842-337e-40ec-bf6c-f902ee956a8b.png) | ![](https://user-images.githubusercontent.com/11482921/164453480-71d5e091-5bfa-4c77-9c57-4e37f66ca0a3.png) | ![](https://user-images.githubusercontent.com/11482921/164453468-c295d3c9-3661-45f0-9ecd-406a1877f76e.png) | ![](https://user-images.githubusercontent.com/11482921/164453486-3091887c-587c-450e-b6fe-905cb518d57e.png) |
+
+**其他更好的结果**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![Japan_v2_1_128525_s1_patch](https://user-images.githubusercontent.com/11482921/164454933-67697f7c-b6ef-47dc-bfca-822a78af8acf.png) | ![](https://user-images.githubusercontent.com/11482921/164454931-9450de7c-f0b3-4638-9c1e-0668e0c41ef0.png) | ![](https://user-images.githubusercontent.com/11482921/164454926-ed746976-786d-41c5-8a83-7693cd774c3a.png) | ![](https://user-images.githubusercontent.com/11482921/164454936-8abdf0f0-fb30-40eb-8281-3b46c0bcb9ae.png) |
+|![tianshuqitan_2_patch](https://user-images.githubusercontent.com/11482921/164456948-807c1476-90b6-4507-81da-cb986d01600c.png) | ![](https://user-images.githubusercontent.com/11482921/164456943-25e89de9-d7e5-4f61-a2e1-96786af6ae9e.png) | ![](https://user-images.githubusercontent.com/11482921/164456954-b468c447-59f5-4594-9693-3683e44ba3e6.png) | ![](https://user-images.githubusercontent.com/11482921/164456957-640f910c-3b04-407c-ac20-044d72e19735.png) |
+|![00000051_patch](https://user-images.githubusercontent.com/11482921/164456044-e9a6b3fa-b24e-4eb7-acf9-1f7746551b1e.png) ![00000051_patch](https://user-images.githubusercontent.com/11482921/164456421-b67245b0-767d-4250-9105-80bbe507ecfc.png) | ![](https://user-images.githubusercontent.com/11482921/164456040-85763cf2-cb28-4ba3-abb6-1dbb48c55713.png) ![](https://user-images.githubusercontent.com/11482921/164456419-59cf342e-bc1e-4044-868c-e1090abad313.png) | ![](https://user-images.githubusercontent.com/11482921/164456031-4244bb7b-8649-4e01-86f4-40c2099c5afd.png) ![](https://user-images.githubusercontent.com/11482921/164456411-b6afcbe9-c054-448d-a6df-96d3ba3047f8.png) | ![](https://user-images.githubusercontent.com/11482921/164456035-12e270be-fd52-46d4-b18a-3d3b680731fe.png) ![](https://user-images.githubusercontent.com/11482921/164456417-dcaa8b62-f497-427d-b2d2-f390f1200fb9.png) |
+|![00000099_patch](https://user-images.githubusercontent.com/11482921/164455312-6411b6e1-5823-4131-a4b0-a6be8a9ae89f.png) | ![](https://user-images.githubusercontent.com/11482921/164455310-f2b99646-3a22-47a4-805b-dc451ac86ddb.png) | ![](https://user-images.githubusercontent.com/11482921/164455294-35471b42-2826-4451-b7ec-6de01344954c.png) | ![](https://user-images.githubusercontent.com/11482921/164455305-fa4c9758-564a-4081-8b4e-f11057a0404d.png) |
+|![00000016_patch](https://user-images.githubusercontent.com/11482921/164455672-447353c9-2da2-4fcb-ba4a-7dd6b94c19c1.png) | ![](https://user-images.githubusercontent.com/11482921/164455669-df384631-baaa-42f8-9150-40f658471558.png) | ![](https://user-images.githubusercontent.com/11482921/164455657-68006bf0-138d-4981-aaca-8aa927d2f78a.png) | ![](https://user-images.githubusercontent.com/11482921/164455664-0342b93e-a62a-4b36-a90e-7118f3f1e45d.png) |
+
+## 推理速度比较
+
+### PyTorch
+
+请注意，我们只报告了**模型推理**的时间, 而忽略了读写硬盘的时间.
+
+| GPU | 输入尺寸 | waifu2x | Real-CUGAN | RealESRGAN-AnimeVideo-v3
+| :---: | :---:         |  :---:        |     :---:      |  :---:      |
+| V100 | 1921 x 1080 | - | 3.4 fps | **10.0** fps |
+| V100 | 1280 x 720 | - | 7.2 fps | **22.6** fps |
+| V100 | 640 x 480 | - | 24.4 fps | **65.9** fps |
+
+### ncnn
+
+- [ ] TODO

docs/anime_model.md

@@ -0,0 +1,68 @@
+# Anime Model
+
+:white_check_mark: We add [*RealESRGAN_x4plus_anime_6B.pth*](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth), which is optimized for **anime** images with much smaller model size.
+
+- [How to Use](#how-to-use)
+  - [PyTorch Inference](#pytorch-inference)
+  - [ncnn Executable File](#ncnn-executable-file)
+- [Comparisons with waifu2x](#comparisons-with-waifu2x)
+- [Comparisons with Sliding Bars](#comparisons-with-sliding-bars)
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+
+The following is a video comparison with sliding bar. You may need to use the full-screen mode for better visual quality, as the original image is large; otherwise, you may encounter aliasing issue.
+
+<https://user-images.githubusercontent.com/17445847/131535127-613250d4-f754-4e20-9720-2f9608ad0675.mp4>
+
+## How to Use
+
+### PyTorch Inference
+
+Pre-trained models: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)
+
+```bash
+# download model
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
+# inference
+python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
+```
+
+### ncnn Executable File
+
+Download the latest portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**.
+
+Taking the Windows as example, run:
+
+```bash
+./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus-anime
+```
+
+## Comparisons with waifu2x
+
+We compare Real-ESRGAN-anime with [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan). We use the `-n 2 -s 4` for waifu2x.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_2.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_3.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_4.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_5.png">
+</p>
+
+## Comparisons with Sliding Bars
+
+The following are video comparisons with sliding bar. You may need to use the full-screen mode for better visual quality, as the original image is large; otherwise, you may encounter aliasing issue.
+
+<https://user-images.githubusercontent.com/17445847/131536647-a2fbf896-b495-4a9f-b1dd-ca7bbc90101a.mp4>
+
+<https://user-images.githubusercontent.com/17445847/131536742-6d9d82b6-9765-4296-a15f-18f9aeaa5465.mp4>

docs/anime_video_model.md

@@ -0,0 +1,136 @@
+# Anime Video Models
+
+:white_check_mark: We add small models that are optimized for anime videos :-)<br>
+More comparisons can be found in [anime_comparisons.md](anime_comparisons.md)
+
+- [How to Use](#how-to-use)
+- [PyTorch Inference](#pytorch-inference)
+- [ncnn Executable File](#ncnn-executable-file)
+  - [Step 1: Use ffmpeg to extract frames from video](#step-1-use-ffmpeg-to-extract-frames-from-video)
+  - [Step 2: Inference with Real-ESRGAN executable file](#step-2-inference-with-real-esrgan-executable-file)
+  - [Step 3: Merge the enhanced frames back into a video](#step-3-merge-the-enhanced-frames-back-into-a-video)
+- [More Demos](#more-demos)
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [realesr-animevideov3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth) | X4 <sup>1</sup>   | Anime video model with XS size |
+
+Note: <br>
+<sup>1</sup> This model can also be used for X1, X2, X3.
+
+---
+
+The following are some demos (best view in the full screen mode).
+
+<https://user-images.githubusercontent.com/17445847/145706977-98bc64a4-af27-481c-8abe-c475e15db7ff.MP4>
+
+<https://user-images.githubusercontent.com/17445847/145707055-6a4b79cb-3d9d-477f-8610-c6be43797133.MP4>
+
+<https://user-images.githubusercontent.com/17445847/145783523-f4553729-9f03-44a8-a7cc-782aadf67b50.MP4>
+
+## How to Use
+
+### PyTorch Inference
+
+```bash
+# download model
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P weights
+# single gpu and single process inference
+CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2
+# single gpu and multi process inference (you can use multi-processing to improve GPU utilization)
+CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
+# multi gpu and multi process inference
+CUDA_VISIBLE_DEVICES=0,1,2,3 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
+```
+
+```console
+Usage:
+--num_process_per_gpu    The total number of process is num_gpu * num_process_per_gpu. The bottleneck of
+                         the program lies on the IO, so the GPUs are usually not fully utilized. To alleviate
+                         this issue, you can use multi-processing by setting this parameter. As long as it
+                         does not exceed the CUDA memory
+--extract_frame_first    If you encounter ffmpeg error when using multi-processing, you can turn this option on.
+```
+
+### NCNN Executable File
+
+#### Step 1: Use ffmpeg to extract frames from video
+
+```bash
+ffmpeg -i onepiece_demo.mp4 -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 tmp_frames/frame%08d.png
+```
+
+- Remember to create the folder `tmp_frames` ahead
+
+#### Step 2: Inference with Real-ESRGAN executable file
+
+1. Download the latest portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**
+
+1. Taking the Windows as example, run:
+
+    ```bash
+    ./realesrgan-ncnn-vulkan.exe -i tmp_frames -o out_frames -n realesr-animevideov3 -s 2 -f jpg
+    ```
+
+    - Remember to create the folder `out_frames` ahead
+
+#### Step 3: Merge the enhanced frames back into a video
+
+1. First obtain fps from input videos by
+
+    ```bash
+    ffmpeg -i onepiece_demo.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path
+    ```
+
+    You will get the output similar to the following screenshot.
+
+    <p align="center">
+        <img src="https://user-images.githubusercontent.com/17445847/145710145-c4f3accf-b82f-4307-9f20-3803a2c73f57.png">
+    </p>
+
+2. Merge frames
+
+    ```bash
+    ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -c:v libx264 -r 23.98 -pix_fmt yuv420p output.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path
+    -c:v                 video encoder (usually we use libx264)
+    -r                   fps, remember to modify it to meet your needs
+    -pix_fmt             pixel format in video
+    ```
+
+    If you also want to copy audio from the input videos, run:
+
+     ```bash
+    ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -i onepiece_demo.mp4 -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r 23.98 -pix_fmt yuv420p output_w_audio.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path, here we use two input streams
+    -c:v                 video encoder (usually we use libx264)
+    -r                   fps, remember to modify it to meet your needs
+    -pix_fmt             pixel format in video
+    ```
+
+## More Demos
+
+- Input video for One Piece:
+
+    <https://user-images.githubusercontent.com/17445847/145706822-0e83d9c4-78ef-40ee-b2a4-d8b8c3692d17.mp4>
+
+- Out video for One Piece
+
+    <https://user-images.githubusercontent.com/17445847/164960481-759658cf-fcb8-480c-b888-cecb606e8744.mp4>
+
+**More comparisons**
+
+<https://user-images.githubusercontent.com/17445847/145707458-04a5e9b9-2edd-4d1f-b400-380a72e5f5e6.MP4>

docs/feedback.md

@@ -0,0 +1,11 @@
+# Feedback 反馈
+
+## 动漫插画模型
+
+1. 视频处理不了: 目前的模型，不是针对视频的，所以视频效果很很不好。我们在探究针对视频的模型了
+1. 景深虚化有问题: 现在的模型把一些景深 和 特意的虚化 都复原了，感觉不好。这个后面我们会考虑把这个信息结合进入。一个简单的做法是识别景深和虚化，然后作为条件告诉神经网络，哪些地方复原强一些，哪些地方复原要弱一些
+1. 不可以调节: 像 Waifu2X 可以调节。可以根据自己的喜好，做调整，但是 Real-ESRGAN-anime 并不可以。导致有些恢复效果过了
+1. 把原来的风格改变了: 不同的动漫插画都有自己的风格，现在的 Real-ESRGAN-anime 倾向于恢复成一种风格（这是受到训练数据集影响的）。风格是动漫很重要的一个要素，所以要尽可能保持
+1. 模型太大: 目前的模型处理太慢，能够更快。这个我们有相关的工作在探究，希望能够尽快有结果，并应用到 Real-ESRGAN 这一系列的模型上
+
+Thanks for the [detailed and valuable feedbacks/suggestions](https://github.com/xinntao/Real-ESRGAN/issues/131) by [2ji3150](https://github.com/2ji3150).

docs/model_zoo.md

@@ -0,0 +1,49 @@
+# :european_castle: Model Zoo
+
+- [For General Images](#for-general-images)
+- [For Anime Images](#for-anime-images)
+- [For Anime Videos](#for-anime-videos)
+
+---
+
+## For General Images
+
+| Models                                                                                                                          | Scale | Description                                  |
+| ------------------------------------------------------------------------------------------------------------------------------- | :---- | :------------------------------------------- |
+| [RealESRGAN_x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)                      | X4    | X4 model for general images                  |
+| [RealESRGAN_x2plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth)                      | X2    | X2 model for general images                  |
+| [RealESRNet_x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth)                      | X4    | X4 model with MSE loss (over-smooth effects) |
+| [official ESRGAN_x4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) | X4    | official ESRGAN model                        |
+| [realesr-general-x4v3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth) | X4 (can also be used for X1, X2, X3) | A tiny small model (consume much fewer GPU memory and time); not too strong deblur and denoise capacity |
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+| Models                                                                                                                 | Corresponding model |
+| ---------------------------------------------------------------------------------------------------------------------- | :------------------ |
+| [RealESRGAN_x4plus_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth) | RealESRGAN_x4plus   |
+| [RealESRGAN_x2plus_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x2plus_netD.pth) | RealESRGAN_x2plus   |
+
+## For Anime Images / Illustrations
+
+| Models                                                                                                                         | Scale | Description                                                 |
+| ------------------------------------------------------------------------------------------------------------------------------ | :---- | :---------------------------------------------------------- |
+| [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth) | X4    | Optimized for anime images; 6 RRDB blocks (smaller network) |
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+| Models                                                                                                                                   | Corresponding model        |
+| ---------------------------------------------------------------------------------------------------------------------------------------- | :------------------------- |
+| [RealESRGAN_x4plus_anime_6B_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B_netD.pth) | RealESRGAN_x4plus_anime_6B |
+
+## For Animation Videos
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [realesr-animevideov3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth) | X4<sup>1</sup>    | Anime video model with XS size |
+
+Note: <br>
+<sup>1</sup> This model can also be used for X1, X2, X3.
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+TODO

docs/ncnn_conversion.md

@@ -0,0 +1,11 @@
+# Instructions on converting to NCNN models
+
+1. Convert to onnx model with `scripts/pytorch2onnx.py`. Remember to modify codes accordingly
+1. Convert onnx model to ncnn model
+    1. `cd ncnn-master\ncnn\build\tools\onnx`
+    1. `onnx2ncnn.exe realesrgan-x4.onnx realesrgan-x4-raw.param realesrgan-x4-raw.bin`
+1. Optimize ncnn model
+    1. fp16 mode
+        1. `cd ncnn-master\ncnn\build\tools`
+        1. `ncnnoptimize.exe realesrgan-x4-raw.param realesrgan-x4-raw.bin realesrgan-x4.param realesrgan-x4.bin 1`
+1. Modify the blob name in `realesrgan-x4.param`: `data` and `output`

inference_realesrgan.py

@@ -2,27 +2,43 @@ import argparse
 import cv2
 import glob
 import os
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.download_util import load_file_from_url
 
 from realesrgan import RealESRGANer
+from realesrgan.archs.srvgg_arch import SRVGGNetCompact
 
 
 def main():
+    """Inference demo for Real-ESRGAN.
+    """
     parser = argparse.ArgumentParser()
-    parser.add_argument('--input', type=str, default='inputs', help='Input image or folder')
+    parser.add_argument('-i', '--input', type=str, default='inputs', help='Input image or folder')
     parser.add_argument(
-        '--model_path',
+        '-n',
+        '--model_name',
         type=str,
-        default='experiments/pretrained_models/RealESRGAN_x4plus.pth',
+        default='RealESRGAN_x4plus',
-        help='Path to the pre-trained model')
+        help=('Model names: RealESRGAN_x4plus | RealESRNet_x4plus | RealESRGAN_x4plus_anime_6B | RealESRGAN_x2plus | '
-    parser.add_argument('--output', type=str, default='results', help='Output folder')
+              'realesr-animevideov3 | realesr-general-x4v3'))
-    parser.add_argument('--netscale', type=int, default=4, help='Upsample scale factor of the network')
+    parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
-    parser.add_argument('--outscale', type=float, default=4, help='The final upsampling scale of the image')
+    parser.add_argument(
+        '-dn',
+        '--denoise_strength',
+        type=float,
+        default=0.5,
+        help=('Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. '
+              'Only used for the realesr-general-x4v3 model'))
+    parser.add_argument('-s', '--outscale', type=float, default=4, help='The final upsampling scale of the image')
+    parser.add_argument(
+        '--model_path', type=str, default=None, help='[Option] Model path. Usually, you do not need to specify it')
     parser.add_argument('--suffix', type=str, default='out', help='Suffix of the restored image')
-    parser.add_argument('--tile', type=int, default=800, help='Tile size, 0 for no tile during testing')
+    parser.add_argument('-t', '--tile', type=int, default=0, help='Tile size, 0 for no tile during testing')
     parser.add_argument('--tile_pad', type=int, default=10, help='Tile padding')
     parser.add_argument('--pre_pad', type=int, default=0, help='Pre padding size at each border')
     parser.add_argument('--face_enhance', action='store_true', help='Use GFPGAN to enhance face')
-    parser.add_argument('--half', action='store_true', help='Use half precision during inference')
+    parser.add_argument(
+        '--fp32', action='store_true', help='Use fp32 precision during inference. Default: fp16 (half precision).')
     parser.add_argument(
         '--alpha_upsampler',
         type=str,
@@ -33,20 +49,76 @@ def main():
         type=str,
         default='auto',
         help='Image extension. Options: auto | jpg | png, auto means using the same extension as inputs')
+    parser.add_argument(
+        '-g', '--gpu-id', type=int, default=None, help='gpu device to use (default=None) can be 0,1,2 for multi-gpu')
+
     args = parser.parse_args()
 
+    # determine models according to model names
+    args.model_name = args.model_name.split('.')[0]
+    if args.model_name == 'RealESRGAN_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth']
+    elif args.model_name == 'RealESRNet_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth']
+    elif args.model_name == 'RealESRGAN_x4plus_anime_6B':  # x4 RRDBNet model with 6 blocks
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth']
+    elif args.model_name == 'RealESRGAN_x2plus':  # x2 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
+        netscale = 2
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth']
+    elif args.model_name == 'realesr-animevideov3':  # x4 VGG-style model (XS size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth']
+    elif args.model_name == 'realesr-general-x4v3':  # x4 VGG-style model (S size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+        netscale = 4
+        file_url = [
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth',
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth'
+        ]
+
+    # determine model paths
+    if args.model_path is not None:
+        model_path = args.model_path
+    else:
+        model_path = os.path.join('weights', args.model_name + '.pth')
+        if not os.path.isfile(model_path):
+            ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
+            for url in file_url:
+                # model_path will be updated
+                model_path = load_file_from_url(
+                    url=url, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
+
+    # use dni to control the denoise strength
+    dni_weight = None
+    if args.model_name == 'realesr-general-x4v3' and args.denoise_strength != 1:
+        wdn_model_path = model_path.replace('realesr-general-x4v3', 'realesr-general-wdn-x4v3')
+        model_path = [model_path, wdn_model_path]
+        dni_weight = [args.denoise_strength, 1 - args.denoise_strength]
+
+    # restorer
     upsampler = RealESRGANer(
-        scale=args.netscale,
+        scale=netscale,
-        model_path=args.model_path,
+        model_path=model_path,
+        dni_weight=dni_weight,
+        model=model,
         tile=args.tile,
         tile_pad=args.tile_pad,
         pre_pad=args.pre_pad,
-        half=args.half)
+        half=not args.fp32,
+        gpu_id=args.gpu_id)
 
-    if args.face_enhance:
+    if args.face_enhance:  # Use GFPGAN for face enhancement
         from gfpgan import GFPGANer
         face_enhancer = GFPGANer(
-            model_path='https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth',
+            model_path='https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth',
             upscale=args.outscale,
             arch='clean',
             channel_multiplier=2,
@@ -68,20 +140,12 @@ def main():
         else:
             img_mode = None
 
-        h, w = img.shape[0:2]
-        if max(h, w) > 1000 and args.netscale == 4:
-            import warnings
-            warnings.warn('The input image is large, try X2 model for better performace.')
-        if max(h, w) < 500 and args.netscale == 2:
-            import warnings
-            warnings.warn('The input image is small, try X4 model for better performace.')
-
         try:
             if args.face_enhance:
                 _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
             else:
                 output, _ = upsampler.enhance(img, outscale=args.outscale)
-        except Exception as error:
+        except RuntimeError as error:
             print('Error', error)
             print('If you encounter CUDA out of memory, try to set --tile with a smaller number.')
         else:
@@ -91,6 +155,9 @@ def main():
                 extension = args.ext
             if img_mode == 'RGBA':  # RGBA images should be saved in png format
                 extension = 'png'
+            if args.suffix == '':
+                save_path = os.path.join(args.output, f'{imgname}.{extension}')
+            else:
                 save_path = os.path.join(args.output, f'{imgname}_{args.suffix}.{extension}')
             cv2.imwrite(save_path, output)
 

inference_realesrgan_video.py

@@ -0,0 +1,398 @@
+import argparse
+import cv2
+import glob
+import mimetypes
+import numpy as np
+import os
+import shutil
+import subprocess
+import torch
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.download_util import load_file_from_url
+from os import path as osp
+from tqdm import tqdm
+
+from realesrgan import RealESRGANer
+from realesrgan.archs.srvgg_arch import SRVGGNetCompact
+
+try:
+    import ffmpeg
+except ImportError:
+    import pip
+    pip.main(['install', '--user', 'ffmpeg-python'])
+    import ffmpeg
+
+
+def get_video_meta_info(video_path):
+    ret = {}
+    probe = ffmpeg.probe(video_path)
+    video_streams = [stream for stream in probe['streams'] if stream['codec_type'] == 'video']
+    has_audio = any(stream['codec_type'] == 'audio' for stream in probe['streams'])
+    ret['width'] = video_streams[0]['width']
+    ret['height'] = video_streams[0]['height']
+    ret['fps'] = eval(video_streams[0]['avg_frame_rate'])
+    ret['audio'] = ffmpeg.input(video_path).audio if has_audio else None
+    ret['nb_frames'] = int(video_streams[0]['nb_frames'])
+    return ret
+
+
+def get_sub_video(args, num_process, process_idx):
+    if num_process == 1:
+        return args.input
+    meta = get_video_meta_info(args.input)
+    duration = int(meta['nb_frames'] / meta['fps'])
+    part_time = duration // num_process
+    print(f'duration: {duration}, part_time: {part_time}')
+    os.makedirs(osp.join(args.output, f'{args.video_name}_inp_tmp_videos'), exist_ok=True)
+    out_path = osp.join(args.output, f'{args.video_name}_inp_tmp_videos', f'{process_idx:03d}.mp4')
+    cmd = [
+        args.ffmpeg_bin, f'-i {args.input}', '-ss', f'{part_time * process_idx}',
+        f'-to {part_time * (process_idx + 1)}' if process_idx != num_process - 1 else '', '-async 1', out_path, '-y'
+    ]
+    print(' '.join(cmd))
+    subprocess.call(' '.join(cmd), shell=True)
+    return out_path
+
+
+class Reader:
+
+    def __init__(self, args, total_workers=1, worker_idx=0):
+        self.args = args
+        input_type = mimetypes.guess_type(args.input)[0]
+        self.input_type = 'folder' if input_type is None else input_type
+        self.paths = []  # for image&folder type
+        self.audio = None
+        self.input_fps = None
+        if self.input_type.startswith('video'):
+            video_path = get_sub_video(args, total_workers, worker_idx)
+            self.stream_reader = (
+                ffmpeg.input(video_path).output('pipe:', format='rawvideo', pix_fmt='bgr24',
+                                                loglevel='error').run_async(
+                                                    pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))
+            meta = get_video_meta_info(video_path)
+            self.width = meta['width']
+            self.height = meta['height']
+            self.input_fps = meta['fps']
+            self.audio = meta['audio']
+            self.nb_frames = meta['nb_frames']
+
+        else:
+            if self.input_type.startswith('image'):
+                self.paths = [args.input]
+            else:
+                paths = sorted(glob.glob(os.path.join(args.input, '*')))
+                tot_frames = len(paths)
+                num_frame_per_worker = tot_frames // total_workers + (1 if tot_frames % total_workers else 0)
+                self.paths = paths[num_frame_per_worker * worker_idx:num_frame_per_worker * (worker_idx + 1)]
+
+            self.nb_frames = len(self.paths)
+            assert self.nb_frames > 0, 'empty folder'
+            from PIL import Image
+            tmp_img = Image.open(self.paths[0])
+            self.width, self.height = tmp_img.size
+        self.idx = 0
+
+    def get_resolution(self):
+        return self.height, self.width
+
+    def get_fps(self):
+        if self.args.fps is not None:
+            return self.args.fps
+        elif self.input_fps is not None:
+            return self.input_fps
+        return 24
+
+    def get_audio(self):
+        return self.audio
+
+    def __len__(self):
+        return self.nb_frames
+
+    def get_frame_from_stream(self):
+        img_bytes = self.stream_reader.stdout.read(self.width * self.height * 3)  # 3 bytes for one pixel
+        if not img_bytes:
+            return None
+        img = np.frombuffer(img_bytes, np.uint8).reshape([self.height, self.width, 3])
+        return img
+
+    def get_frame_from_list(self):
+        if self.idx >= self.nb_frames:
+            return None
+        img = cv2.imread(self.paths[self.idx])
+        self.idx += 1
+        return img
+
+    def get_frame(self):
+        if self.input_type.startswith('video'):
+            return self.get_frame_from_stream()
+        else:
+            return self.get_frame_from_list()
+
+    def close(self):
+        if self.input_type.startswith('video'):
+            self.stream_reader.stdin.close()
+            self.stream_reader.wait()
+
+
+class Writer:
+
+    def __init__(self, args, audio, height, width, video_save_path, fps):
+        out_width, out_height = int(width * args.outscale), int(height * args.outscale)
+        if out_height > 2160:
+            print('You are generating video that is larger than 4K, which will be very slow due to IO speed.',
+                  'We highly recommend to decrease the outscale(aka, -s).')
+
+        if audio is not None:
+            self.stream_writer = (
+                ffmpeg.input('pipe:', format='rawvideo', pix_fmt='bgr24', s=f'{out_width}x{out_height}',
+                             framerate=fps).output(
+                                 audio,
+                                 video_save_path,
+                                 pix_fmt='yuv420p',
+                                 vcodec='libx264',
+                                 loglevel='error',
+                                 acodec='copy').overwrite_output().run_async(
+                                     pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))
+        else:
+            self.stream_writer = (
+                ffmpeg.input('pipe:', format='rawvideo', pix_fmt='bgr24', s=f'{out_width}x{out_height}',
+                             framerate=fps).output(
+                                 video_save_path, pix_fmt='yuv420p', vcodec='libx264',
+                                 loglevel='error').overwrite_output().run_async(
+                                     pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))
+
+    def write_frame(self, frame):
+        frame = frame.astype(np.uint8).tobytes()
+        self.stream_writer.stdin.write(frame)
+
+    def close(self):
+        self.stream_writer.stdin.close()
+        self.stream_writer.wait()
+
+
+def inference_video(args, video_save_path, device=None, total_workers=1, worker_idx=0):
+    # ---------------------- determine models according to model names ---------------------- #
+    args.model_name = args.model_name.split('.pth')[0]
+    if args.model_name == 'RealESRGAN_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth']
+    elif args.model_name == 'RealESRNet_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth']
+    elif args.model_name == 'RealESRGAN_x4plus_anime_6B':  # x4 RRDBNet model with 6 blocks
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth']
+    elif args.model_name == 'RealESRGAN_x2plus':  # x2 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
+        netscale = 2
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth']
+    elif args.model_name == 'realesr-animevideov3':  # x4 VGG-style model (XS size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth']
+    elif args.model_name == 'realesr-general-x4v3':  # x4 VGG-style model (S size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+        netscale = 4
+        file_url = [
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth',
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth'
+        ]
+
+    # ---------------------- determine model paths ---------------------- #
+    model_path = os.path.join('weights', args.model_name + '.pth')
+    if not os.path.isfile(model_path):
+        ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
+        for url in file_url:
+            # model_path will be updated
+            model_path = load_file_from_url(
+                url=url, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
+
+    # use dni to control the denoise strength
+    dni_weight = None
+    if args.model_name == 'realesr-general-x4v3' and args.denoise_strength != 1:
+        wdn_model_path = model_path.replace('realesr-general-x4v3', 'realesr-general-wdn-x4v3')
+        model_path = [model_path, wdn_model_path]
+        dni_weight = [args.denoise_strength, 1 - args.denoise_strength]
+
+    # restorer
+    upsampler = RealESRGANer(
+        scale=netscale,
+        model_path=model_path,
+        dni_weight=dni_weight,
+        model=model,
+        tile=args.tile,
+        tile_pad=args.tile_pad,
+        pre_pad=args.pre_pad,
+        half=not args.fp32,
+        device=device,
+    )
+
+    if 'anime' in args.model_name and args.face_enhance:
+        print('face_enhance is not supported in anime models, we turned this option off for you. '
+              'if you insist on turning it on, please manually comment the relevant lines of code.')
+        args.face_enhance = False
+
+    if args.face_enhance:  # Use GFPGAN for face enhancement
+        from gfpgan import GFPGANer
+        face_enhancer = GFPGANer(
+            model_path='https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth',
+            upscale=args.outscale,
+            arch='clean',
+            channel_multiplier=2,
+            bg_upsampler=upsampler)  # TODO support custom device
+    else:
+        face_enhancer = None
+
+    reader = Reader(args, total_workers, worker_idx)
+    audio = reader.get_audio()
+    height, width = reader.get_resolution()
+    fps = reader.get_fps()
+    writer = Writer(args, audio, height, width, video_save_path, fps)
+
+    pbar = tqdm(total=len(reader), unit='frame', desc='inference')
+    while True:
+        img = reader.get_frame()
+        if img is None:
+            break
+
+        try:
+            if args.face_enhance:
+                _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
+            else:
+                output, _ = upsampler.enhance(img, outscale=args.outscale)
+        except RuntimeError as error:
+            print('Error', error)
+            print('If you encounter CUDA out of memory, try to set --tile with a smaller number.')
+        else:
+            writer.write_frame(output)
+
+        torch.cuda.synchronize(device)
+        pbar.update(1)
+
+    reader.close()
+    writer.close()
+
+
+def run(args):
+    args.video_name = osp.splitext(os.path.basename(args.input))[0]
+    video_save_path = osp.join(args.output, f'{args.video_name}_{args.suffix}.mp4')
+
+    if args.extract_frame_first:
+        tmp_frames_folder = osp.join(args.output, f'{args.video_name}_inp_tmp_frames')
+        os.makedirs(tmp_frames_folder, exist_ok=True)
+        os.system(f'ffmpeg -i {args.input} -qscale:v 1 -qmin 1 -qmax 1 -vsync 0  {tmp_frames_folder}/frame%08d.png')
+        args.input = tmp_frames_folder
+
+    num_gpus = torch.cuda.device_count()
+    num_process = num_gpus * args.num_process_per_gpu
+    if num_process == 1:
+        inference_video(args, video_save_path)
+        return
+
+    ctx = torch.multiprocessing.get_context('spawn')
+    pool = ctx.Pool(num_process)
+    os.makedirs(osp.join(args.output, f'{args.video_name}_out_tmp_videos'), exist_ok=True)
+    pbar = tqdm(total=num_process, unit='sub_video', desc='inference')
+    for i in range(num_process):
+        sub_video_save_path = osp.join(args.output, f'{args.video_name}_out_tmp_videos', f'{i:03d}.mp4')
+        pool.apply_async(
+            inference_video,
+            args=(args, sub_video_save_path, torch.device(i % num_gpus), num_process, i),
+            callback=lambda arg: pbar.update(1))
+    pool.close()
+    pool.join()
+
+    # combine sub videos
+    # prepare vidlist.txt
+    with open(f'{args.output}/{args.video_name}_vidlist.txt', 'w') as f:
+        for i in range(num_process):
+            f.write(f'file \'{args.video_name}_out_tmp_videos/{i:03d}.mp4\'\n')
+
+    cmd = [
+        args.ffmpeg_bin, '-f', 'concat', '-safe', '0', '-i', f'{args.output}/{args.video_name}_vidlist.txt', '-c',
+        'copy', f'{video_save_path}'
+    ]
+    print(' '.join(cmd))
+    subprocess.call(cmd)
+    shutil.rmtree(osp.join(args.output, f'{args.video_name}_out_tmp_videos'))
+    if osp.exists(osp.join(args.output, f'{args.video_name}_inp_tmp_videos')):
+        shutil.rmtree(osp.join(args.output, f'{args.video_name}_inp_tmp_videos'))
+    os.remove(f'{args.output}/{args.video_name}_vidlist.txt')
+
+
+def main():
+    """Inference demo for Real-ESRGAN.
+    It mainly for restoring anime videos.
+
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i', '--input', type=str, default='inputs', help='Input video, image or folder')
+    parser.add_argument(
+        '-n',
+        '--model_name',
+        type=str,
+        default='realesr-animevideov3',
+        help=('Model names: realesr-animevideov3 | RealESRGAN_x4plus_anime_6B | RealESRGAN_x4plus | RealESRNet_x4plus |'
+              ' RealESRGAN_x2plus | realesr-general-x4v3'
+              'Default:realesr-animevideov3'))
+    parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
+    parser.add_argument(
+        '-dn',
+        '--denoise_strength',
+        type=float,
+        default=0.5,
+        help=('Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. '
+              'Only used for the realesr-general-x4v3 model'))
+    parser.add_argument('-s', '--outscale', type=float, default=4, help='The final upsampling scale of the image')
+    parser.add_argument('--suffix', type=str, default='out', help='Suffix of the restored video')
+    parser.add_argument('-t', '--tile', type=int, default=0, help='Tile size, 0 for no tile during testing')
+    parser.add_argument('--tile_pad', type=int, default=10, help='Tile padding')
+    parser.add_argument('--pre_pad', type=int, default=0, help='Pre padding size at each border')
+    parser.add_argument('--face_enhance', action='store_true', help='Use GFPGAN to enhance face')
+    parser.add_argument(
+        '--fp32', action='store_true', help='Use fp32 precision during inference. Default: fp16 (half precision).')
+    parser.add_argument('--fps', type=float, default=None, help='FPS of the output video')
+    parser.add_argument('--ffmpeg_bin', type=str, default='ffmpeg', help='The path to ffmpeg')
+    parser.add_argument('--extract_frame_first', action='store_true')
+    parser.add_argument('--num_process_per_gpu', type=int, default=1)
+
+    parser.add_argument(
+        '--alpha_upsampler',
+        type=str,
+        default='realesrgan',
+        help='The upsampler for the alpha channels. Options: realesrgan | bicubic')
+    parser.add_argument(
+        '--ext',
+        type=str,
+        default='auto',
+        help='Image extension. Options: auto | jpg | png, auto means using the same extension as inputs')
+    args = parser.parse_args()
+
+    args.input = args.input.rstrip('/').rstrip('\\')
+    os.makedirs(args.output, exist_ok=True)
+
+    if mimetypes.guess_type(args.input)[0] is not None and mimetypes.guess_type(args.input)[0].startswith('video'):
+        is_video = True
+    else:
+        is_video = False
+
+    if is_video and args.input.endswith('.flv'):
+        mp4_path = args.input.replace('.flv', '.mp4')
+        os.system(f'ffmpeg -i {args.input} -codec copy {mp4_path}')
+        args.input = mp4_path
+
+    if args.extract_frame_first and not is_video:
+        args.extract_frame_first = False
+
+    run(args)
+
+    if args.extract_frame_first:
+        tmp_frames_folder = osp.join(args.output, f'{args.video_name}_inp_tmp_frames')
+        shutil.rmtree(tmp_frames_folder)
+
+
+if __name__ == '__main__':
+    main()

options/finetune_realesrgan_x4plus.yml

@@ -1,8 +1,8 @@
 # general settings
-name: finetune_RealESRGANx4plus_400k_B12G4
+name: finetune_RealESRGANx4plus_400k
 model_type: RealESRGANModel
 scale: 4
-num_gpu: 4
+num_gpu: auto
 manual_seed: 0
 
 # ----------------- options for synthesizing training data in RealESRGANModel ----------------- #
@@ -90,7 +90,6 @@ network_g:
   num_block: 23
   num_grow_ch: 32
 
-
 network_d:
   type: UNetDiscriminatorSN
   num_in_ch: 3
@@ -169,7 +168,7 @@ train:
 #   save_img: True
 
 #   metrics:
-#     psnr: # metric name, can be arbitrary
+#     psnr: # metric name
 #       type: calculate_psnr
 #       crop_border: 4
 #       test_y_channel: false

options/finetune_realesrgan_x4plus_pairdata.yml

@@ -0,0 +1,150 @@
+# general settings
+name: finetune_RealESRGANx4plus_400k_pairdata
+model_type: RealESRGANModel
+scale: 4
+num_gpu: auto
+manual_seed: 0
+
+# USM the ground-truth
+l1_gt_usm: True
+percep_gt_usm: True
+gan_gt_usm: False
+
+high_order_degradation: False # do not use the high-order degradation generation process
+
+# dataset and data loader settings
+datasets:
+  train:
+    name: DIV2K
+    type: RealESRGANPairedDataset
+    dataroot_gt: datasets/DF2K
+    dataroot_lq: datasets/DF2K
+    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
+    io_backend:
+      type: disk
+
+    gt_size: 256
+    use_hflip: True
+    use_rot: False
+
+    # data loader
+    use_shuffle: true
+    num_worker_per_gpu: 5
+    batch_size_per_gpu: 12
+    dataset_enlarge_ratio: 1
+    prefetch_mode: ~
+
+  # Uncomment these for validation
+  # val:
+  #   name: validation
+  #   type: PairedImageDataset
+  #   dataroot_gt: path_to_gt
+  #   dataroot_lq: path_to_lq
+  #   io_backend:
+  #     type: disk
+
+# network structures
+network_g:
+  type: RRDBNet
+  num_in_ch: 3
+  num_out_ch: 3
+  num_feat: 64
+  num_block: 23
+  num_grow_ch: 32
+
+network_d:
+  type: UNetDiscriminatorSN
+  num_in_ch: 3
+  num_feat: 64
+  skip_connection: True
+
+# path
+path:
+  # use the pre-trained Real-ESRNet model
+  pretrain_network_g: experiments/pretrained_models/RealESRNet_x4plus.pth
+  param_key_g: params_ema
+  strict_load_g: true
+  pretrain_network_d: experiments/pretrained_models/RealESRGAN_x4plus_netD.pth
+  param_key_d: params
+  strict_load_d: true
+  resume_state: ~
+
+# training settings
+train:
+  ema_decay: 0.999
+  optim_g:
+    type: Adam
+    lr: !!float 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.99]
+  optim_d:
+    type: Adam
+    lr: !!float 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.99]
+
+  scheduler:
+    type: MultiStepLR
+    milestones: [400000]
+    gamma: 0.5
+
+  total_iter: 400000
+  warmup_iter: -1  # no warm up
+
+  # losses
+  pixel_opt:
+    type: L1Loss
+    loss_weight: 1.0
+    reduction: mean
+  # perceptual loss (content and style losses)
+  perceptual_opt:
+    type: PerceptualLoss
+    layer_weights:
+      # before relu
+      'conv1_2': 0.1
+      'conv2_2': 0.1
+      'conv3_4': 1
+      'conv4_4': 1
+      'conv5_4': 1
+    vgg_type: vgg19
+    use_input_norm: true
+    perceptual_weight: !!float 1.0
+    style_weight: 0
+    range_norm: false
+    criterion: l1
+  # gan loss
+  gan_opt:
+    type: GANLoss
+    gan_type: vanilla
+    real_label_val: 1.0
+    fake_label_val: 0.0
+    loss_weight: !!float 1e-1
+
+  net_d_iters: 1
+  net_d_init_iters: 0
+
+# Uncomment these for validation
+# validation settings
+# val:
+#   val_freq: !!float 5e3
+#   save_img: True
+
+#   metrics:
+#     psnr: # metric name
+#       type: calculate_psnr
+#       crop_border: 4
+#       test_y_channel: false
+
+# logging settings
+logger:
+  print_freq: 100
+  save_checkpoint_freq: !!float 5e3
+  use_tb_logger: true
+  wandb:
+    project: ~
+    resume_id: ~
+
+# dist training settings
+dist_params:
+  backend: nccl
+  port: 29500

options/train_realesrgan_x2plus.yml

@@ -2,7 +2,7 @@
 name: train_RealESRGANx2plus_400k_B12G4
 model_type: RealESRGANModel
 scale: 2
-num_gpu: 4
+num_gpu: auto  # auto: can infer from your visible devices automatically. official: 4 GPUs
 manual_seed: 0
 
 # ----------------- options for synthesizing training data in RealESRGANModel ----------------- #
@@ -91,7 +91,6 @@ network_g:
   num_grow_ch: 32
   scale: 2
 
-
 network_d:
   type: UNetDiscriminatorSN
   num_in_ch: 3
@@ -167,7 +166,7 @@ train:
 #   save_img: True
 
 #   metrics:
-#     psnr: # metric name, can be arbitrary
+#     psnr: # metric name
 #       type: calculate_psnr
 #       crop_border: 4
 #       test_y_channel: false

options/train_realesrgan_x4plus.yml

@@ -2,7 +2,7 @@
 name: train_RealESRGANx4plus_400k_B12G4
 model_type: RealESRGANModel
 scale: 4
-num_gpu: 4
+num_gpu: auto  # auto: can infer from your visible devices automatically. official: 4 GPUs
 manual_seed: 0
 
 # ----------------- options for synthesizing training data in RealESRGANModel ----------------- #
@@ -90,7 +90,6 @@ network_g:
   num_block: 23
   num_grow_ch: 32
 
-
 network_d:
   type: UNetDiscriminatorSN
   num_in_ch: 3
@@ -166,7 +165,7 @@ train:
 #   save_img: True
 
 #   metrics:
-#     psnr: # metric name, can be arbitrary
+#     psnr: # metric name
 #       type: calculate_psnr
 #       crop_border: 4
 #       test_y_channel: false

options/train_realesrnet_x2plus.yml

@@ -2,7 +2,7 @@
 name: train_RealESRNetx2plus_1000k_B12G4
 model_type: RealESRNetModel
 scale: 2
-num_gpu: 4
+num_gpu: auto  # auto: can infer from your visible devices automatically. official: 4 GPUs
 manual_seed: 0
 
 # ----------------- options for synthesizing training data in RealESRNetModel ----------------- #
@@ -125,7 +125,7 @@ train:
 #   save_img: True
 
 #   metrics:
-#     psnr: # metric name, can be arbitrary
+#     psnr: # metric name
 #       type: calculate_psnr
 #       crop_border: 4
 #       test_y_channel: false

options/train_realesrnet_x4plus.yml

@@ -2,7 +2,7 @@
 name: train_RealESRNetx4plus_1000k_B12G4
 model_type: RealESRNetModel
 scale: 4
-num_gpu: 4
+num_gpu: auto  # auto: can infer from your visible devices automatically. official: 4 GPUs
 manual_seed: 0
 
 # ----------------- options for synthesizing training data in RealESRNetModel ----------------- #
@@ -124,7 +124,7 @@ train:
 #   save_img: True
 
 #   metrics:
-#     psnr: # metric name, can be arbitrary
+#     psnr: # metric name
 #       type: calculate_psnr
 #       crop_border: 4
 #       test_y_channel: false

realesrgan/__init__.py

@@ -3,4 +3,4 @@ from .archs import *
 from .data import *
 from .models import *
 from .utils import *
-from .version import __gitsha__, __version__
+from .version import *

realesrgan/archs/discriminator_arch.py

@@ -6,15 +6,23 @@ from torch.nn.utils import spectral_norm
 
 @ARCH_REGISTRY.register()
 class UNetDiscriminatorSN(nn.Module):
-    """Defines a U-Net discriminator with spectral normalization (SN)"""
+    """Defines a U-Net discriminator with spectral normalization (SN)
+
+    It is used in Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data.
+
+    Arg:
+        num_in_ch (int): Channel number of inputs. Default: 3.
+        num_feat (int): Channel number of base intermediate features. Default: 64.
+        skip_connection (bool): Whether to use skip connections between U-Net. Default: True.
+    """
 
     def __init__(self, num_in_ch, num_feat=64, skip_connection=True):
         super(UNetDiscriminatorSN, self).__init__()
         self.skip_connection = skip_connection
         norm = spectral_norm
-
+        # the first convolution
         self.conv0 = nn.Conv2d(num_in_ch, num_feat, kernel_size=3, stride=1, padding=1)
-
+        # downsample
         self.conv1 = norm(nn.Conv2d(num_feat, num_feat * 2, 4, 2, 1, bias=False))
         self.conv2 = norm(nn.Conv2d(num_feat * 2, num_feat * 4, 4, 2, 1, bias=False))
         self.conv3 = norm(nn.Conv2d(num_feat * 4, num_feat * 8, 4, 2, 1, bias=False))
@@ -22,14 +30,13 @@ class UNetDiscriminatorSN(nn.Module):
         self.conv4 = norm(nn.Conv2d(num_feat * 8, num_feat * 4, 3, 1, 1, bias=False))
         self.conv5 = norm(nn.Conv2d(num_feat * 4, num_feat * 2, 3, 1, 1, bias=False))
         self.conv6 = norm(nn.Conv2d(num_feat * 2, num_feat, 3, 1, 1, bias=False))
-
+        # extra convolutions
-        # extra
         self.conv7 = norm(nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=False))
         self.conv8 = norm(nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=False))
-
         self.conv9 = nn.Conv2d(num_feat, 1, 3, 1, 1)
 
     def forward(self, x):
+        # downsample
         x0 = F.leaky_relu(self.conv0(x), negative_slope=0.2, inplace=True)
         x1 = F.leaky_relu(self.conv1(x0), negative_slope=0.2, inplace=True)
         x2 = F.leaky_relu(self.conv2(x1), negative_slope=0.2, inplace=True)
@@ -52,7 +59,7 @@ class UNetDiscriminatorSN(nn.Module):
         if self.skip_connection:
             x6 = x6 + x0
 
-        # extra
+        # extra convolutions
         out = F.leaky_relu(self.conv7(x6), negative_slope=0.2, inplace=True)
         out = F.leaky_relu(self.conv8(out), negative_slope=0.2, inplace=True)
         out = self.conv9(out)

realesrgan/archs/srvgg_arch.py

@@ -0,0 +1,69 @@
+from basicsr.utils.registry import ARCH_REGISTRY
+from torch import nn as nn
+from torch.nn import functional as F
+
+
+@ARCH_REGISTRY.register()
+class SRVGGNetCompact(nn.Module):
+    """A compact VGG-style network structure for super-resolution.
+
+    It is a compact network structure, which performs upsampling in the last layer and no convolution is
+    conducted on the HR feature space.
+
+    Args:
+        num_in_ch (int): Channel number of inputs. Default: 3.
+        num_out_ch (int): Channel number of outputs. Default: 3.
+        num_feat (int): Channel number of intermediate features. Default: 64.
+        num_conv (int): Number of convolution layers in the body network. Default: 16.
+        upscale (int): Upsampling factor. Default: 4.
+        act_type (str): Activation type, options: 'relu', 'prelu', 'leakyrelu'. Default: prelu.
+    """
+
+    def __init__(self, num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu'):
+        super(SRVGGNetCompact, self).__init__()
+        self.num_in_ch = num_in_ch
+        self.num_out_ch = num_out_ch
+        self.num_feat = num_feat
+        self.num_conv = num_conv
+        self.upscale = upscale
+        self.act_type = act_type
+
+        self.body = nn.ModuleList()
+        # the first conv
+        self.body.append(nn.Conv2d(num_in_ch, num_feat, 3, 1, 1))
+        # the first activation
+        if act_type == 'relu':
+            activation = nn.ReLU(inplace=True)
+        elif act_type == 'prelu':
+            activation = nn.PReLU(num_parameters=num_feat)
+        elif act_type == 'leakyrelu':
+            activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
+        self.body.append(activation)
+
+        # the body structure
+        for _ in range(num_conv):
+            self.body.append(nn.Conv2d(num_feat, num_feat, 3, 1, 1))
+            # activation
+            if act_type == 'relu':
+                activation = nn.ReLU(inplace=True)
+            elif act_type == 'prelu':
+                activation = nn.PReLU(num_parameters=num_feat)
+            elif act_type == 'leakyrelu':
+                activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
+            self.body.append(activation)
+
+        # the last conv
+        self.body.append(nn.Conv2d(num_feat, num_out_ch * upscale * upscale, 3, 1, 1))
+        # upsample
+        self.upsampler = nn.PixelShuffle(upscale)
+
+    def forward(self, x):
+        out = x
+        for i in range(0, len(self.body)):
+            out = self.body[i](out)
+
+        out = self.upsampler(out)
+        # add the nearest upsampled image, so that the network learns the residual
+        base = F.interpolate(x, scale_factor=self.upscale, mode='nearest')
+        out += base
+        return out

realesrgan/data/realesrgan_dataset.py

@@ -15,18 +15,31 @@ from torch.utils import data as data
 
 @DATASET_REGISTRY.register()
 class RealESRGANDataset(data.Dataset):
-    """
+    """Dataset used for Real-ESRGAN model:
-    Dataset used for Real-ESRGAN model.
+    Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data.
+
+    It loads gt (Ground-Truth) images, and augments them.
+    It also generates blur kernels and sinc kernels for generating low-quality images.
+    Note that the low-quality images are processed in tensors on GPUS for faster processing.
+
+    Args:
+        opt (dict): Config for train datasets. It contains the following keys:
+            dataroot_gt (str): Data root path for gt.
+            meta_info (str): Path for meta information file.
+            io_backend (dict): IO backend type and other kwarg.
+            use_hflip (bool): Use horizontal flips.
+            use_rot (bool): Use rotation (use vertical flip and transposing h and w for implementation).
+            Please see more options in the codes.
     """
 
     def __init__(self, opt):
         super(RealESRGANDataset, self).__init__()
         self.opt = opt
-        # file client (io backend)
         self.file_client = None
         self.io_backend_opt = opt['io_backend']
         self.gt_folder = opt['dataroot_gt']
 
+        # file client (lmdb io backend)
         if self.io_backend_opt['type'] == 'lmdb':
             self.io_backend_opt['db_paths'] = [self.gt_folder]
             self.io_backend_opt['client_keys'] = ['gt']
@@ -35,18 +48,20 @@ class RealESRGANDataset(data.Dataset):
             with open(osp.join(self.gt_folder, 'meta_info.txt')) as fin:
                 self.paths = [line.split('.')[0] for line in fin]
         else:
+            # disk backend with meta_info
+            # Each line in the meta_info describes the relative path to an image
             with open(self.opt['meta_info']) as fin:
-                paths = [line.strip() for line in fin]
+                paths = [line.strip().split(' ')[0] for line in fin]
                 self.paths = [os.path.join(self.gt_folder, v) for v in paths]
 
         # blur settings for the first degradation
         self.blur_kernel_size = opt['blur_kernel_size']
         self.kernel_list = opt['kernel_list']
-        self.kernel_prob = opt['kernel_prob']
+        self.kernel_prob = opt['kernel_prob']  # a list for each kernel probability
         self.blur_sigma = opt['blur_sigma']
-        self.betag_range = opt['betag_range']
+        self.betag_range = opt['betag_range']  # betag used in generalized Gaussian blur kernels
-        self.betap_range = opt['betap_range']
+        self.betap_range = opt['betap_range']  # betap used in plateau blur kernels
-        self.sinc_prob = opt['sinc_prob']
+        self.sinc_prob = opt['sinc_prob']  # the probability for sinc filters
 
         # blur settings for the second degradation
         self.blur_kernel_size2 = opt['blur_kernel_size2']
@@ -61,6 +76,7 @@ class RealESRGANDataset(data.Dataset):
         self.final_sinc_prob = opt['final_sinc_prob']
 
         self.kernel_range = [2 * v + 1 for v in range(3, 11)]  # kernel size ranges from 7 to 21
+        # TODO: kernel range is now hard-coded, should be in the configure file
         self.pulse_tensor = torch.zeros(21, 21).float()  # convolving with pulse tensor brings no blurry effect
         self.pulse_tensor[10, 10] = 1
 
@@ -76,7 +92,7 @@ class RealESRGANDataset(data.Dataset):
         while retry > 0:
             try:
                 img_bytes = self.file_client.get(gt_path, 'gt')
-            except Exception as e:
+            except (IOError, OSError) as e:
                 logger = get_root_logger()
                 logger.warn(f'File client error: {e}, remaining retry times: {retry - 1}')
                 # change another file to read
@@ -89,10 +105,11 @@ class RealESRGANDataset(data.Dataset):
                 retry -= 1
         img_gt = imfrombytes(img_bytes, float32=True)
 
-        # -------------------- augmentation for training: flip, rotation -------------------- #
+        # -------------------- Do augmentation for training: flip, rotation -------------------- #
         img_gt = augment(img_gt, self.opt['use_hflip'], self.opt['use_rot'])
 
-        # crop or pad to 400: 400 is hard-coded. You may change it accordingly
+        # crop or pad to 400
+        # TODO: 400 is hard-coded. You may change it accordingly
         h, w = img_gt.shape[0:2]
         crop_pad_size = 400
         # pad
@@ -154,7 +171,7 @@ class RealESRGANDataset(data.Dataset):
         pad_size = (21 - kernel_size) // 2
         kernel2 = np.pad(kernel2, ((pad_size, pad_size), (pad_size, pad_size)))
 
-        # ------------------------------------- sinc kernel ------------------------------------- #
+        # ------------------------------------- the final sinc kernel ------------------------------------- #
         if np.random.uniform() < self.opt['final_sinc_prob']:
             kernel_size = random.choice(self.kernel_range)
             omega_c = np.random.uniform(np.pi / 3, np.pi)

realesrgan/data/realesrgan_paired_dataset.py

@@ -0,0 +1,108 @@
+import os
+from basicsr.data.data_util import paired_paths_from_folder, paired_paths_from_lmdb
+from basicsr.data.transforms import augment, paired_random_crop
+from basicsr.utils import FileClient, imfrombytes, img2tensor
+from basicsr.utils.registry import DATASET_REGISTRY
+from torch.utils import data as data
+from torchvision.transforms.functional import normalize
+
+
+@DATASET_REGISTRY.register()
+class RealESRGANPairedDataset(data.Dataset):
+    """Paired image dataset for image restoration.
+
+    Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs.
+
+    There are three modes:
+    1. 'lmdb': Use lmdb files.
+        If opt['io_backend'] == lmdb.
+    2. 'meta_info': Use meta information file to generate paths.
+        If opt['io_backend'] != lmdb and opt['meta_info'] is not None.
+    3. 'folder': Scan folders to generate paths.
+        The rest.
+
+    Args:
+        opt (dict): Config for train datasets. It contains the following keys:
+            dataroot_gt (str): Data root path for gt.
+            dataroot_lq (str): Data root path for lq.
+            meta_info (str): Path for meta information file.
+            io_backend (dict): IO backend type and other kwarg.
+            filename_tmpl (str): Template for each filename. Note that the template excludes the file extension.
+                Default: '{}'.
+            gt_size (int): Cropped patched size for gt patches.
+            use_hflip (bool): Use horizontal flips.
+            use_rot (bool): Use rotation (use vertical flip and transposing h
+                and w for implementation).
+
+            scale (bool): Scale, which will be added automatically.
+            phase (str): 'train' or 'val'.
+    """
+
+    def __init__(self, opt):
+        super(RealESRGANPairedDataset, self).__init__()
+        self.opt = opt
+        self.file_client = None
+        self.io_backend_opt = opt['io_backend']
+        # mean and std for normalizing the input images
+        self.mean = opt['mean'] if 'mean' in opt else None
+        self.std = opt['std'] if 'std' in opt else None
+
+        self.gt_folder, self.lq_folder = opt['dataroot_gt'], opt['dataroot_lq']
+        self.filename_tmpl = opt['filename_tmpl'] if 'filename_tmpl' in opt else '{}'
+
+        # file client (lmdb io backend)
+        if self.io_backend_opt['type'] == 'lmdb':
+            self.io_backend_opt['db_paths'] = [self.lq_folder, self.gt_folder]
+            self.io_backend_opt['client_keys'] = ['lq', 'gt']
+            self.paths = paired_paths_from_lmdb([self.lq_folder, self.gt_folder], ['lq', 'gt'])
+        elif 'meta_info' in self.opt and self.opt['meta_info'] is not None:
+            # disk backend with meta_info
+            # Each line in the meta_info describes the relative path to an image
+            with open(self.opt['meta_info']) as fin:
+                paths = [line.strip() for line in fin]
+            self.paths = []
+            for path in paths:
+                gt_path, lq_path = path.split(', ')
+                gt_path = os.path.join(self.gt_folder, gt_path)
+                lq_path = os.path.join(self.lq_folder, lq_path)
+                self.paths.append(dict([('gt_path', gt_path), ('lq_path', lq_path)]))
+        else:
+            # disk backend
+            # it will scan the whole folder to get meta info
+            # it will be time-consuming for folders with too many files. It is recommended using an extra meta txt file
+            self.paths = paired_paths_from_folder([self.lq_folder, self.gt_folder], ['lq', 'gt'], self.filename_tmpl)
+
+    def __getitem__(self, index):
+        if self.file_client is None:
+            self.file_client = FileClient(self.io_backend_opt.pop('type'), **self.io_backend_opt)
+
+        scale = self.opt['scale']
+
+        # Load gt and lq images. Dimension order: HWC; channel order: BGR;
+        # image range: [0, 1], float32.
+        gt_path = self.paths[index]['gt_path']
+        img_bytes = self.file_client.get(gt_path, 'gt')
+        img_gt = imfrombytes(img_bytes, float32=True)
+        lq_path = self.paths[index]['lq_path']
+        img_bytes = self.file_client.get(lq_path, 'lq')
+        img_lq = imfrombytes(img_bytes, float32=True)
+
+        # augmentation for training
+        if self.opt['phase'] == 'train':
+            gt_size = self.opt['gt_size']
+            # random crop
+            img_gt, img_lq = paired_random_crop(img_gt, img_lq, gt_size, scale, gt_path)
+            # flip, rotation
+            img_gt, img_lq = augment([img_gt, img_lq], self.opt['use_hflip'], self.opt['use_rot'])
+
+        # BGR to RGB, HWC to CHW, numpy to tensor
+        img_gt, img_lq = img2tensor([img_gt, img_lq], bgr2rgb=True, float32=True)
+        # normalize
+        if self.mean is not None or self.std is not None:
+            normalize(img_lq, self.mean, self.std, inplace=True)
+            normalize(img_gt, self.mean, self.std, inplace=True)
+
+        return {'lq': img_lq, 'gt': img_gt, 'lq_path': lq_path, 'gt_path': gt_path}
+
+    def __len__(self):
+        return len(self.paths)

realesrgan/models/realesrgan_model.py

@@ -13,35 +13,45 @@ from torch.nn import functional as F
 
 @MODEL_REGISTRY.register()
 class RealESRGANModel(SRGANModel):
-    """RealESRGAN Model"""
+    """RealESRGAN Model for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data.
+
+    It mainly performs:
+    1. randomly synthesize LQ images in GPU tensors
+    2. optimize the networks with GAN training.
+    """
 
     def __init__(self, opt):
         super(RealESRGANModel, self).__init__(opt)
-        self.jpeger = DiffJPEG(differentiable=False).cuda()
+        self.jpeger = DiffJPEG(differentiable=False).cuda()  # simulate JPEG compression artifacts
-        self.usm_sharpener = USMSharp().cuda()
+        self.usm_sharpener = USMSharp().cuda()  # do usm sharpening
-        self.queue_size = opt['queue_size']
+        self.queue_size = opt.get('queue_size', 180)
 
     @torch.no_grad()
     def _dequeue_and_enqueue(self):
-        # training pair pool
+        """It is the training pair pool for increasing the diversity in a batch.
+
+        Batch processing limits the diversity of synthetic degradations in a batch. For example, samples in a
+        batch could not have different resize scaling factors. Therefore, we employ this training pair pool
+        to increase the degradation diversity in a batch.
+        """
         # initialize
         b, c, h, w = self.lq.size()
         if not hasattr(self, 'queue_lr'):
-            assert self.queue_size % b == 0, 'queue size should be divisible by batch size'
+            assert self.queue_size % b == 0, f'queue size {self.queue_size} should be divisible by batch size {b}'
             self.queue_lr = torch.zeros(self.queue_size, c, h, w).cuda()
             _, c, h, w = self.gt.size()
             self.queue_gt = torch.zeros(self.queue_size, c, h, w).cuda()
             self.queue_ptr = 0
-        if self.queue_ptr == self.queue_size:  # full
+        if self.queue_ptr == self.queue_size:  # the pool is full
             # do dequeue and enqueue
             # shuffle
             idx = torch.randperm(self.queue_size)
             self.queue_lr = self.queue_lr[idx]
             self.queue_gt = self.queue_gt[idx]
-            # get
+            # get first b samples
             lq_dequeue = self.queue_lr[0:b, :, :, :].clone()
             gt_dequeue = self.queue_gt[0:b, :, :, :].clone()
-            # update
+            # update the queue
             self.queue_lr[0:b, :, :, :] = self.lq.clone()
             self.queue_gt[0:b, :, :, :] = self.gt.clone()
 
@@ -55,7 +65,9 @@ class RealESRGANModel(SRGANModel):
 
     @torch.no_grad()
     def feed_data(self, data):
-        if self.is_train:
+        """Accept data from dataloader, and then add two-order degradations to obtain LQ images.
+        """
+        if self.is_train and self.opt.get('high_order_degradation', True):
             # training data synthesis
             self.gt = data['gt'].to(self.device)
             self.gt_usm = self.usm_sharpener(self.gt)
@@ -79,7 +91,7 @@ class RealESRGANModel(SRGANModel):
                 scale = 1
             mode = random.choice(['area', 'bilinear', 'bicubic'])
             out = F.interpolate(out, scale_factor=scale, mode=mode)
-            # noise
+            # add noise
             gray_noise_prob = self.opt['gray_noise_prob']
             if np.random.uniform() < self.opt['gaussian_noise_prob']:
                 out = random_add_gaussian_noise_pt(
@@ -93,7 +105,7 @@ class RealESRGANModel(SRGANModel):
                     rounds=False)
             # JPEG compression
             jpeg_p = out.new_zeros(out.size(0)).uniform_(*self.opt['jpeg_range'])
-            out = torch.clamp(out, 0, 1)
+            out = torch.clamp(out, 0, 1)  # clamp to [0, 1], otherwise JPEGer will result in unpleasant artifacts
             out = self.jpeger(out, quality=jpeg_p)
 
             # ----------------------- The second degradation process ----------------------- #
@@ -111,7 +123,7 @@ class RealESRGANModel(SRGANModel):
             mode = random.choice(['area', 'bilinear', 'bicubic'])
             out = F.interpolate(
                 out, size=(int(ori_h / self.opt['scale'] * scale), int(ori_w / self.opt['scale'] * scale)), mode=mode)
-            # noise
+            # add noise
             gray_noise_prob = self.opt['gray_noise_prob2']
             if np.random.uniform() < self.opt['gaussian_noise_prob2']:
                 out = random_add_gaussian_noise_pt(
@@ -162,10 +174,13 @@ class RealESRGANModel(SRGANModel):
             self._dequeue_and_enqueue()
             # sharpen self.gt again, as we have changed the self.gt with self._dequeue_and_enqueue
             self.gt_usm = self.usm_sharpener(self.gt)
+            self.lq = self.lq.contiguous()  # for the warning: grad and param do not obey the gradient layout contract
         else:
+            # for paired training or validation
             self.lq = data['lq'].to(self.device)
             if 'gt' in data:
                 self.gt = data['gt'].to(self.device)
+                self.gt_usm = self.usm_sharpener(self.gt)
 
     def nondist_validation(self, dataloader, current_iter, tb_logger, save_img):
         # do not use the synthetic process during validation
@@ -174,6 +189,7 @@ class RealESRGANModel(SRGANModel):
         self.is_train = True
 
     def optimize_parameters(self, current_iter):
+        # usm sharpening
         l1_gt = self.gt_usm
         percep_gt = self.gt_usm
         gan_gt = self.gt_usm

realesrgan/models/realesrnet_model.py

@@ -12,35 +12,46 @@ from torch.nn import functional as F
 
 @MODEL_REGISTRY.register()
 class RealESRNetModel(SRModel):
-    """RealESRNet Model"""
+    """RealESRNet Model for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data.
+
+    It is trained without GAN losses.
+    It mainly performs:
+    1. randomly synthesize LQ images in GPU tensors
+    2. optimize the networks with GAN training.
+    """
 
     def __init__(self, opt):
         super(RealESRNetModel, self).__init__(opt)
-        self.jpeger = DiffJPEG(differentiable=False).cuda()
+        self.jpeger = DiffJPEG(differentiable=False).cuda()  # simulate JPEG compression artifacts
-        self.usm_sharpener = USMSharp().cuda()
+        self.usm_sharpener = USMSharp().cuda()  # do usm sharpening
-        self.queue_size = opt['queue_size']
+        self.queue_size = opt.get('queue_size', 180)
 
     @torch.no_grad()
     def _dequeue_and_enqueue(self):
-        # training pair pool
+        """It is the training pair pool for increasing the diversity in a batch.
+
+        Batch processing limits the diversity of synthetic degradations in a batch. For example, samples in a
+        batch could not have different resize scaling factors. Therefore, we employ this training pair pool
+        to increase the degradation diversity in a batch.
+        """
         # initialize
         b, c, h, w = self.lq.size()
         if not hasattr(self, 'queue_lr'):
-            assert self.queue_size % b == 0, 'queue size should be divisible by batch size'
+            assert self.queue_size % b == 0, f'queue size {self.queue_size} should be divisible by batch size {b}'
             self.queue_lr = torch.zeros(self.queue_size, c, h, w).cuda()
             _, c, h, w = self.gt.size()
             self.queue_gt = torch.zeros(self.queue_size, c, h, w).cuda()
             self.queue_ptr = 0
-        if self.queue_ptr == self.queue_size:  # full
+        if self.queue_ptr == self.queue_size:  # the pool is full
             # do dequeue and enqueue
             # shuffle
             idx = torch.randperm(self.queue_size)
             self.queue_lr = self.queue_lr[idx]
             self.queue_gt = self.queue_gt[idx]
-            # get
+            # get first b samples
             lq_dequeue = self.queue_lr[0:b, :, :, :].clone()
             gt_dequeue = self.queue_gt[0:b, :, :, :].clone()
-            # update
+            # update the queue
             self.queue_lr[0:b, :, :, :] = self.lq.clone()
             self.queue_gt[0:b, :, :, :] = self.gt.clone()
 
@@ -54,10 +65,12 @@ class RealESRNetModel(SRModel):
 
     @torch.no_grad()
     def feed_data(self, data):
-        if self.is_train:
+        """Accept data from dataloader, and then add two-order degradations to obtain LQ images.
+        """
+        if self.is_train and self.opt.get('high_order_degradation', True):
             # training data synthesis
             self.gt = data['gt'].to(self.device)
-            # USM the GT images
+            # USM sharpen the GT images
             if self.opt['gt_usm'] is True:
                 self.gt = self.usm_sharpener(self.gt)
 
@@ -80,7 +93,7 @@ class RealESRNetModel(SRModel):
                 scale = 1
             mode = random.choice(['area', 'bilinear', 'bicubic'])
             out = F.interpolate(out, scale_factor=scale, mode=mode)
-            # noise
+            # add noise
             gray_noise_prob = self.opt['gray_noise_prob']
             if np.random.uniform() < self.opt['gaussian_noise_prob']:
                 out = random_add_gaussian_noise_pt(
@@ -94,7 +107,7 @@ class RealESRNetModel(SRModel):
                     rounds=False)
             # JPEG compression
             jpeg_p = out.new_zeros(out.size(0)).uniform_(*self.opt['jpeg_range'])
-            out = torch.clamp(out, 0, 1)
+            out = torch.clamp(out, 0, 1)  # clamp to [0, 1], otherwise JPEGer will result in unpleasant artifacts
             out = self.jpeger(out, quality=jpeg_p)
 
             # ----------------------- The second degradation process ----------------------- #
@@ -112,7 +125,7 @@ class RealESRNetModel(SRModel):
             mode = random.choice(['area', 'bilinear', 'bicubic'])
             out = F.interpolate(
                 out, size=(int(ori_h / self.opt['scale'] * scale), int(ori_w / self.opt['scale'] * scale)), mode=mode)
-            # noise
+            # add noise
             gray_noise_prob = self.opt['gray_noise_prob2']
             if np.random.uniform() < self.opt['gaussian_noise_prob2']:
                 out = random_add_gaussian_noise_pt(
@@ -160,10 +173,13 @@ class RealESRNetModel(SRModel):
 
             # training pair pool
             self._dequeue_and_enqueue()
+            self.lq = self.lq.contiguous()  # for the warning: grad and param do not obey the gradient layout contract
         else:
+            # for paired training or validation
             self.lq = data['lq'].to(self.device)
             if 'gt' in data:
                 self.gt = data['gt'].to(self.device)
+                self.gt_usm = self.usm_sharpener(self.gt)
 
     def nondist_validation(self, dataloader, current_iter, tb_logger, save_img):
         # do not use the synthetic process during validation

realesrgan/utils.py

@@ -2,18 +2,41 @@ import cv2
 import math
 import numpy as np
 import os
+import queue
+import threading
 import torch
-from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.download_util import load_file_from_url
-from torch.hub import download_url_to_file, get_dir
 from torch.nn import functional as F
-from urllib.parse import urlparse
 
 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
 
 class RealESRGANer():
+    """A helper class for upsampling images with RealESRGAN.
 
-    def __init__(self, scale, model_path, tile=0, tile_pad=10, pre_pad=10, half=False):
+    Args:
+        scale (int): Upsampling scale factor used in the networks. It is usually 2 or 4.
+        model_path (str): The path to the pretrained model. It can be urls (will first download it automatically).
+        model (nn.Module): The defined network. Default: None.
+        tile (int): As too large images result in the out of GPU memory issue, so this tile option will first crop
+            input images into tiles, and then process each of them. Finally, they will be merged into one image.
+            0 denotes for do not use tile. Default: 0.
+        tile_pad (int): The pad size for each tile, to remove border artifacts. Default: 10.
+        pre_pad (int): Pad the input images to avoid border artifacts. Default: 10.
+        half (float): Whether to use half precision during inference. Default: False.
+    """
+
+    def __init__(self,
+                 scale,
+                 model_path,
+                 dni_weight=None,
+                 model=None,
+                 tile=0,
+                 tile_pad=10,
+                 pre_pad=10,
+                 half=False,
+                 device=None,
+                 gpu_id=None):
         self.scale = scale
         self.tile_size = tile
         self.tile_pad = tile_pad
@@ -22,24 +45,49 @@ class RealESRGANer():
         self.half = half
 
         # initialize model
-        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        if gpu_id:
-        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=scale)
+            self.device = torch.device(
+                f'cuda:{gpu_id}' if torch.cuda.is_available() else 'cpu') if device is None else device
+        else:
+            self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if device is None else device
 
+        if isinstance(model_path, list):
+            # dni
+            assert len(model_path) == len(dni_weight), 'model_path and dni_weight should have the save length.'
+            loadnet = self.dni(model_path[0], model_path[1], dni_weight)
+        else:
+            # if the model_path starts with https, it will first download models to the folder: weights
             if model_path.startswith('https://'):
                 model_path = load_file_from_url(
-                url=model_path, model_dir='realesrgan/weights', progress=True, file_name=None)
+                    url=model_path, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
-        loadnet = torch.load(model_path)
+            loadnet = torch.load(model_path, map_location=torch.device('cpu'))
+
+        # prefer to use params_ema
         if 'params_ema' in loadnet:
             keyname = 'params_ema'
         else:
             keyname = 'params'
         model.load_state_dict(loadnet[keyname], strict=True)
+
         model.eval()
         self.model = model.to(self.device)
         if self.half:
             self.model = self.model.half()
 
+    def dni(self, net_a, net_b, dni_weight, key='params', loc='cpu'):
+        """Deep network interpolation.
+
+        ``Paper: Deep Network Interpolation for Continuous Imagery Effect Transition``
+        """
+        net_a = torch.load(net_a, map_location=torch.device(loc))
+        net_b = torch.load(net_b, map_location=torch.device(loc))
+        for k, v_a in net_a[key].items():
+            net_a[key][k] = dni_weight[0] * v_a + dni_weight[1] * net_b[key][k]
+        return net_a
+
     def pre_process(self, img):
+        """Pre-process, such as pre-pad and mod pad, so that the images can be divisible
+        """
         img = torch.from_numpy(np.transpose(img, (2, 0, 1))).float()
         self.img = img.unsqueeze(0).to(self.device)
         if self.half:
@@ -48,7 +96,7 @@ class RealESRGANer():
         # pre_pad
         if self.pre_pad != 0:
             self.img = F.pad(self.img, (0, self.pre_pad, 0, self.pre_pad), 'reflect')
-        # mod pad
+        # mod pad for divisible borders
         if self.scale == 2:
             self.mod_scale = 2
         elif self.scale == 1:
@@ -63,10 +111,14 @@ class RealESRGANer():
             self.img = F.pad(self.img, (0, self.mod_pad_w, 0, self.mod_pad_h), 'reflect')
 
     def process(self):
+        # model inference
         self.output = self.model(self.img)
 
     def tile_process(self):
-        """Modified from: https://github.com/ata4/esrgan-launcher
+        """It will first crop input images to tiles, and then process each tile.
+        Finally, all the processed tiles are merged into one images.
+
+        Modified from: https://github.com/ata4/esrgan-launcher
         """
         batch, channel, height, width = self.img.shape
         output_height = height * self.scale
@@ -106,7 +158,7 @@ class RealESRGANer():
                 try:
                     with torch.no_grad():
                         output_tile = self.model(input_tile)
-                except Exception as error:
+                except RuntimeError as error:
                     print('Error', error)
                 print(f'\tTile {tile_idx}/{tiles_x * tiles_y}')
 
@@ -187,7 +239,7 @@ class RealESRGANer():
                 output_alpha = output_alpha.data.squeeze().float().cpu().clamp_(0, 1).numpy()
                 output_alpha = np.transpose(output_alpha[[2, 1, 0], :, :], (1, 2, 0))
                 output_alpha = cv2.cvtColor(output_alpha, cv2.COLOR_BGR2GRAY)
-            else:
+            else:  # use the cv2 resize for alpha channel
                 h, w = alpha.shape[0:2]
                 output_alpha = cv2.resize(alpha, (w * self.scale, h * self.scale), interpolation=cv2.INTER_LINEAR)
 
@@ -211,21 +263,51 @@ class RealESRGANer():
         return output, img_mode
 
 
-def load_file_from_url(url, model_dir=None, progress=True, file_name=None):
+class PrefetchReader(threading.Thread):
-    """Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py
+    """Prefetch images.
+
+    Args:
+        img_list (list[str]): A image list of image paths to be read.
+        num_prefetch_queue (int): Number of prefetch queue.
     """
-    if model_dir is None:
-        hub_dir = get_dir()
-        model_dir = os.path.join(hub_dir, 'checkpoints')
 
-    os.makedirs(os.path.join(ROOT_DIR, model_dir), exist_ok=True)
+    def __init__(self, img_list, num_prefetch_queue):
+        super().__init__()
+        self.que = queue.Queue(num_prefetch_queue)
+        self.img_list = img_list
 
-    parts = urlparse(url)
+    def run(self):
-    filename = os.path.basename(parts.path)
+        for img_path in self.img_list:
-    if file_name is not None:
+            img = cv2.imread(img_path, cv2.IMREAD_UNCHANGED)
-        filename = file_name
+            self.que.put(img)
-    cached_file = os.path.abspath(os.path.join(ROOT_DIR, model_dir, filename))
+
-    if not os.path.exists(cached_file):
+        self.que.put(None)
-        print(f'Downloading: "{url}" to {cached_file}\n')
+
-        download_url_to_file(url, cached_file, hash_prefix=None, progress=progress)
+    def __next__(self):
-    return cached_file
+        next_item = self.que.get()
+        if next_item is None:
+            raise StopIteration
+        return next_item
+
+    def __iter__(self):
+        return self
+
+
+class IOConsumer(threading.Thread):
+
+    def __init__(self, opt, que, qid):
+        super().__init__()
+        self._queue = que
+        self.qid = qid
+        self.opt = opt
+
+    def run(self):
+        while True:
+            msg = self._queue.get()
+            if isinstance(msg, str) and msg == 'quit':
+                break
+
+            output = msg['output']
+            save_path = msg['save_path']
+            cv2.imwrite(save_path, output)
+        print(f'IO worker {self.qid} is done.')

requirements.txt

@@ -1,7 +1,9 @@
-basicsr>=1.3.3.11
+basicsr>=1.4.2
-facexlib>=0.2.0.3
+facexlib>=0.2.5
-gfpgan>=0.2.1
+gfpgan>=1.3.5
 numpy
 opencv-python
 Pillow
 torch>=1.7
+torchvision
+tqdm

scripts/extract_subimages.py

@@ -0,0 +1,135 @@
+import argparse
+import cv2
+import numpy as np
+import os
+import sys
+from basicsr.utils import scandir
+from multiprocessing import Pool
+from os import path as osp
+from tqdm import tqdm
+
+
+def main(args):
+    """A multi-thread tool to crop large images to sub-images for faster IO.
+
+    opt (dict): Configuration dict. It contains:
+        n_thread (int): Thread number.
+        compression_level (int):  CV_IMWRITE_PNG_COMPRESSION from 0 to 9. A higher value means a smaller size
+            and longer compression time. Use 0 for faster CPU decompression. Default: 3, same in cv2.
+        input_folder (str): Path to the input folder.
+        save_folder (str): Path to save folder.
+        crop_size (int): Crop size.
+        step (int): Step for overlapped sliding window.
+        thresh_size (int): Threshold size. Patches whose size is lower than thresh_size will be dropped.
+
+    Usage:
+        For each folder, run this script.
+        Typically, there are GT folder and LQ folder to be processed for DIV2K dataset.
+        After process, each sub_folder should have the same number of subimages.
+        Remember to modify opt configurations according to your settings.
+    """
+
+    opt = {}
+    opt['n_thread'] = args.n_thread
+    opt['compression_level'] = args.compression_level
+    opt['input_folder'] = args.input
+    opt['save_folder'] = args.output
+    opt['crop_size'] = args.crop_size
+    opt['step'] = args.step
+    opt['thresh_size'] = args.thresh_size
+    extract_subimages(opt)
+
+
+def extract_subimages(opt):
+    """Crop images to subimages.
+
+    Args:
+        opt (dict): Configuration dict. It contains:
+            input_folder (str): Path to the input folder.
+            save_folder (str): Path to save folder.
+            n_thread (int): Thread number.
+    """
+    input_folder = opt['input_folder']
+    save_folder = opt['save_folder']
+    if not osp.exists(save_folder):
+        os.makedirs(save_folder)
+        print(f'mkdir {save_folder} ...')
+    else:
+        print(f'Folder {save_folder} already exists. Exit.')
+        sys.exit(1)
+
+    # scan all images
+    img_list = list(scandir(input_folder, full_path=True))
+
+    pbar = tqdm(total=len(img_list), unit='image', desc='Extract')
+    pool = Pool(opt['n_thread'])
+    for path in img_list:
+        pool.apply_async(worker, args=(path, opt), callback=lambda arg: pbar.update(1))
+    pool.close()
+    pool.join()
+    pbar.close()
+    print('All processes done.')
+
+
+def worker(path, opt):
+    """Worker for each process.
+
+    Args:
+        path (str): Image path.
+        opt (dict): Configuration dict. It contains:
+            crop_size (int): Crop size.
+            step (int): Step for overlapped sliding window.
+            thresh_size (int): Threshold size. Patches whose size is lower than thresh_size will be dropped.
+            save_folder (str): Path to save folder.
+            compression_level (int): for cv2.IMWRITE_PNG_COMPRESSION.
+
+    Returns:
+        process_info (str): Process information displayed in progress bar.
+    """
+    crop_size = opt['crop_size']
+    step = opt['step']
+    thresh_size = opt['thresh_size']
+    img_name, extension = osp.splitext(osp.basename(path))
+
+    # remove the x2, x3, x4 and x8 in the filename for DIV2K
+    img_name = img_name.replace('x2', '').replace('x3', '').replace('x4', '').replace('x8', '')
+
+    img = cv2.imread(path, cv2.IMREAD_UNCHANGED)
+
+    h, w = img.shape[0:2]
+    h_space = np.arange(0, h - crop_size + 1, step)
+    if h - (h_space[-1] + crop_size) > thresh_size:
+        h_space = np.append(h_space, h - crop_size)
+    w_space = np.arange(0, w - crop_size + 1, step)
+    if w - (w_space[-1] + crop_size) > thresh_size:
+        w_space = np.append(w_space, w - crop_size)
+
+    index = 0
+    for x in h_space:
+        for y in w_space:
+            index += 1
+            cropped_img = img[x:x + crop_size, y:y + crop_size, ...]
+            cropped_img = np.ascontiguousarray(cropped_img)
+            cv2.imwrite(
+                osp.join(opt['save_folder'], f'{img_name}_s{index:03d}{extension}'), cropped_img,
+                [cv2.IMWRITE_PNG_COMPRESSION, opt['compression_level']])
+    process_info = f'Processing {img_name} ...'
+    return process_info
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', type=str, default='datasets/DF2K/DF2K_HR', help='Input folder')
+    parser.add_argument('--output', type=str, default='datasets/DF2K/DF2K_HR_sub', help='Output folder')
+    parser.add_argument('--crop_size', type=int, default=480, help='Crop size')
+    parser.add_argument('--step', type=int, default=240, help='Step for overlapped sliding window')
+    parser.add_argument(
+        '--thresh_size',
+        type=int,
+        default=0,
+        help='Threshold size. Patches whose size is lower than thresh_size will be dropped.')
+    parser.add_argument('--n_thread', type=int, default=20, help='Thread number.')
+    parser.add_argument('--compression_level', type=int, default=3, help='Compression level')
+    args = parser.parse_args()
+
+    main(args)

scripts/generate_meta_info.py

@@ -1,4 +1,5 @@
 import argparse
+import cv2
 import glob
 import os
 
@@ -8,6 +9,19 @@ def main(args):
     for folder, root in zip(args.input, args.root):
         img_paths = sorted(glob.glob(os.path.join(folder, '*')))
         for img_path in img_paths:
+            status = True
+            if args.check:
+                # read the image once for check, as some images may have errors
+                try:
+                    img = cv2.imread(img_path)
+                except (IOError, OSError) as error:
+                    print(f'Read {img_path} error: {error}')
+                    status = False
+                if img is None:
+                    status = False
+                    print(f'Img is None: {img_path}')
+            if status:
+                # get the relative path
                 img_name = os.path.relpath(img_path, root)
                 print(img_name)
                 txt_file.write(f'{img_name}\n')
@@ -34,7 +48,11 @@ if __name__ == '__main__':
         type=str,
         default='datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt',
         help='txt path for meta info')
+    parser.add_argument('--check', action='store_true', help='Read image to check whether it is ok')
     args = parser.parse_args()
+
     assert len(args.input) == len(args.root), ('Input folder and folder root should have the same length, but got '
                                                f'{len(args.input)} and {len(args.root)}.')
+    os.makedirs(os.path.dirname(args.meta_info), exist_ok=True)
+
     main(args)

scripts/generate_meta_info_pairdata.py

@@ -0,0 +1,49 @@
+import argparse
+import glob
+import os
+
+
+def main(args):
+    txt_file = open(args.meta_info, 'w')
+    # sca images
+    img_paths_gt = sorted(glob.glob(os.path.join(args.input[0], '*')))
+    img_paths_lq = sorted(glob.glob(os.path.join(args.input[1], '*')))
+
+    assert len(img_paths_gt) == len(img_paths_lq), ('GT folder and LQ folder should have the same length, but got '
+                                                    f'{len(img_paths_gt)} and {len(img_paths_lq)}.')
+
+    for img_path_gt, img_path_lq in zip(img_paths_gt, img_paths_lq):
+        # get the relative paths
+        img_name_gt = os.path.relpath(img_path_gt, args.root[0])
+        img_name_lq = os.path.relpath(img_path_lq, args.root[1])
+        print(f'{img_name_gt}, {img_name_lq}')
+        txt_file.write(f'{img_name_gt}, {img_name_lq}\n')
+
+
+if __name__ == '__main__':
+    """This script is used to generate meta info (txt file) for paired images.
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--input',
+        nargs='+',
+        default=['datasets/DF2K/DIV2K_train_HR_sub', 'datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub'],
+        help='Input folder, should be [gt_folder, lq_folder]')
+    parser.add_argument('--root', nargs='+', default=[None, None], help='Folder root, will use the ')
+    parser.add_argument(
+        '--meta_info',
+        type=str,
+        default='datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt',
+        help='txt path for meta info')
+    args = parser.parse_args()
+
+    assert len(args.input) == 2, 'Input folder should have two elements: gt folder and lq folder'
+    assert len(args.root) == 2, 'Root path should have two elements: root for gt folder and lq folder'
+    os.makedirs(os.path.dirname(args.meta_info), exist_ok=True)
+    for i in range(2):
+        if args.input[i].endswith('/'):
+            args.input[i] = args.input[i][:-1]
+        if args.root[i] is None:
+            args.root[i] = os.path.dirname(args.input[i])
+
+    main(args)

scripts/generate_multiscale_DF2K.py

@@ -5,7 +5,6 @@ from PIL import Image
 
 
 def main(args):
-
     # For DF2K, we consider the following three scales,
     # and the smallest image whose shortest edge is 400
     scale_list = [0.75, 0.5, 1 / 3]
@@ -37,6 +36,9 @@ def main(args):
 
 
 if __name__ == '__main__':
+    """Generate multi-scale versions for GT images with LANCZOS resampling.
+    It is now used for DF2K dataset (DIV2K + Flickr 2K)
+    """
     parser = argparse.ArgumentParser()
     parser.add_argument('--input', type=str, default='datasets/DF2K/DF2K_HR', help='Input folder')
     parser.add_argument('--output', type=str, default='datasets/DF2K/DF2K_multiscale', help='Output folder')

scripts/pytorch2onnx.py

@@ -1,17 +1,36 @@
+import argparse
 import torch
 import torch.onnx
 from basicsr.archs.rrdbnet_arch import RRDBNet
 
-# An instance of your model
-model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32)
-model.load_state_dict(torch.load('experiments/pretrained_models/RealESRGAN_x4plus.pth')['params_ema'])
-# set the train mode to false since we will only run the forward pass.
-model.train(False)
-model.cpu().eval()
 
-# An example input you would normally provide to your model's forward() method
+def main(args):
-x = torch.rand(1, 3, 64, 64)
+    # An instance of the model
+    model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+    if args.params:
+        keyname = 'params'
+    else:
+        keyname = 'params_ema'
+    model.load_state_dict(torch.load(args.input)[keyname])
+    # set the train mode to false since we will only run the forward pass.
+    model.train(False)
+    model.cpu().eval()
 
-# Export the model
+    # An example input
-with torch.no_grad():
+    x = torch.rand(1, 3, 64, 64)
-    torch_out = torch.onnx._export(model, x, 'realesrgan-x4.onnx', opset_version=11, export_params=True)
+    # Export the model
+    with torch.no_grad():
+        torch_out = torch.onnx._export(model, x, args.output, opset_version=11, export_params=True)
+    print(torch_out.shape)
+
+
+if __name__ == '__main__':
+    """Convert pytorch model to onnx models"""
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--input', type=str, default='experiments/pretrained_models/RealESRGAN_x4plus.pth', help='Input model path')
+    parser.add_argument('--output', type=str, default='realesrgan-x4.onnx', help='Output onnx path')
+    parser.add_argument('--params', action='store_false', help='Use params instead of params_ema')
+    args = parser.parse_args()
+
+    main(args)

setup.cfg

@@ -17,6 +17,17 @@ line_length = 120
 multi_line_output = 0
 known_standard_library = pkg_resources,setuptools
 known_first_party = realesrgan
-known_third_party = PIL,basicsr,cv2,numpy,torch
+known_third_party = PIL,basicsr,cv2,numpy,pytest,torch,torchvision,tqdm,yaml
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY
+
+[codespell]
+skip = .git,./docs/build
+count =
+quiet-level = 3
+
+[aliases]
+test=pytest
+
+[tool:pytest]
+addopts=tests/

setup.py

@@ -43,12 +43,6 @@ def get_git_hash():
 def get_hash():
     if os.path.exists('.git'):
         sha = get_git_hash()[:7]
-    elif os.path.exists(version_file):
-        try:
-            from facexlib.version import __version__
-            sha = __version__.split('+')[-1]
-        except ImportError:
-            raise ImportError('Unable to get git version')
     else:
         sha = 'unknown'
 

tests/data/gt.lmdb/meta_info.txt

@@ -0,0 +1,2 @@
+baboon.png (480,500,3) 1
+comic.png (360,240,3) 1

tests/data/lq.lmdb/meta_info.txt

@@ -0,0 +1,2 @@
+baboon.png (120,125,3) 1
+comic.png (80,60,3) 1

tests/data/meta_info_gt.txt

@@ -0,0 +1,2 @@
+baboon.png
+comic.png

tests/data/meta_info_pair.txt

@@ -0,0 +1,2 @@
+gt/baboon.png, lq/baboon.png
+gt/comic.png, lq/comic.png

tests/data/test_realesrgan_dataset.yml

@@ -0,0 +1,28 @@
+name: Demo
+type: RealESRGANDataset
+dataroot_gt: tests/data/gt
+meta_info: tests/data/meta_info_gt.txt
+io_backend:
+  type: disk
+
+blur_kernel_size: 21
+kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
+kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
+sinc_prob: 1
+blur_sigma: [0.2, 3]
+betag_range: [0.5, 4]
+betap_range: [1, 2]
+
+blur_kernel_size2: 21
+kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
+kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
+sinc_prob2: 1
+blur_sigma2: [0.2, 1.5]
+betag_range2: [0.5, 4]
+betap_range2: [1, 2]
+
+final_sinc_prob: 1
+
+gt_size: 128
+use_hflip: True
+use_rot: False

tests/data/test_realesrgan_model.yml

@@ -0,0 +1,115 @@
+scale: 4
+num_gpu: 1
+manual_seed: 0
+is_train: True
+dist: False
+
+# ----------------- options for synthesizing training data ----------------- #
+# USM the ground-truth
+l1_gt_usm: True
+percep_gt_usm: True
+gan_gt_usm: False
+
+# the first degradation process
+resize_prob: [0.2, 0.7, 0.1]  # up, down, keep
+resize_range: [0.15, 1.5]
+gaussian_noise_prob: 1
+noise_range: [1, 30]
+poisson_scale_range: [0.05, 3]
+gray_noise_prob: 1
+jpeg_range: [30, 95]
+
+# the second degradation process
+second_blur_prob: 1
+resize_prob2: [0.3, 0.4, 0.3]  # up, down, keep
+resize_range2: [0.3, 1.2]
+gaussian_noise_prob2: 1
+noise_range2: [1, 25]
+poisson_scale_range2: [0.05, 2.5]
+gray_noise_prob2: 1
+jpeg_range2: [30, 95]
+
+gt_size: 32
+queue_size: 1
+
+# network structures
+network_g:
+  type: RRDBNet
+  num_in_ch: 3
+  num_out_ch: 3
+  num_feat: 4
+  num_block: 1
+  num_grow_ch: 2
+
+network_d:
+  type: UNetDiscriminatorSN
+  num_in_ch: 3
+  num_feat: 2
+  skip_connection: True
+
+# path
+path:
+  pretrain_network_g: ~
+  param_key_g: params_ema
+  strict_load_g: true
+  resume_state: ~
+
+# training settings
+train:
+  ema_decay: 0.999
+  optim_g:
+    type: Adam
+    lr: !!float 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.99]
+  optim_d:
+    type: Adam
+    lr: !!float 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.99]
+
+  scheduler:
+    type: MultiStepLR
+    milestones: [400000]
+    gamma: 0.5
+
+  total_iter: 400000
+  warmup_iter: -1  # no warm up
+
+  # losses
+  pixel_opt:
+    type: L1Loss
+    loss_weight: 1.0
+    reduction: mean
+  # perceptual loss (content and style losses)
+  perceptual_opt:
+    type: PerceptualLoss
+    layer_weights:
+      # before relu
+      'conv1_2': 0.1
+      'conv2_2': 0.1
+      'conv3_4': 1
+      'conv4_4': 1
+      'conv5_4': 1
+    vgg_type: vgg19
+    use_input_norm: true
+    perceptual_weight: !!float 1.0
+    style_weight: 0
+    range_norm: false
+    criterion: l1
+  # gan loss
+  gan_opt:
+    type: GANLoss
+    gan_type: vanilla
+    real_label_val: 1.0
+    fake_label_val: 0.0
+    loss_weight: !!float 1e-1
+
+  net_d_iters: 1
+  net_d_init_iters: 0
+
+
+# validation settings
+val:
+  val_freq: !!float 5e3
+  save_img: False

tests/data/test_realesrgan_paired_dataset.yml

@@ -0,0 +1,13 @@
+name: Demo
+type: RealESRGANPairedDataset
+scale: 4
+dataroot_gt: tests/data
+dataroot_lq: tests/data
+meta_info: tests/data/meta_info_pair.txt
+io_backend:
+  type: disk
+
+phase: train
+gt_size: 128
+use_hflip: True
+use_rot: False

tests/data/test_realesrnet_model.yml

@@ -0,0 +1,75 @@
+scale: 4
+num_gpu: 1
+manual_seed: 0
+is_train: True
+dist: False
+
+# ----------------- options for synthesizing training data ----------------- #
+gt_usm: True  # USM the ground-truth
+
+# the first degradation process
+resize_prob: [0.2, 0.7, 0.1]  # up, down, keep
+resize_range: [0.15, 1.5]
+gaussian_noise_prob: 1
+noise_range: [1, 30]
+poisson_scale_range: [0.05, 3]
+gray_noise_prob: 1
+jpeg_range: [30, 95]
+
+# the second degradation process
+second_blur_prob: 1
+resize_prob2: [0.3, 0.4, 0.3]  # up, down, keep
+resize_range2: [0.3, 1.2]
+gaussian_noise_prob2: 1
+noise_range2: [1, 25]
+poisson_scale_range2: [0.05, 2.5]
+gray_noise_prob2: 1
+jpeg_range2: [30, 95]
+
+gt_size: 32
+queue_size: 1
+
+# network structures
+network_g:
+  type: RRDBNet
+  num_in_ch: 3
+  num_out_ch: 3
+  num_feat: 4
+  num_block: 1
+  num_grow_ch: 2
+
+# path
+path:
+  pretrain_network_g: ~
+  param_key_g: params_ema
+  strict_load_g: true
+  resume_state: ~
+
+# training settings
+train:
+  ema_decay: 0.999
+  optim_g:
+    type: Adam
+    lr: !!float 2e-4
+    weight_decay: 0
+    betas: [0.9, 0.99]
+
+  scheduler:
+    type: MultiStepLR
+    milestones: [1000000]
+    gamma: 0.5
+
+  total_iter: 1000000
+  warmup_iter: -1  # no warm up
+
+  # losses
+  pixel_opt:
+    type: L1Loss
+    loss_weight: 1.0
+    reduction: mean
+
+
+# validation settings
+val:
+  val_freq: !!float 5e3
+  save_img: False

tests/test_dataset.py

@@ -0,0 +1,151 @@
+import pytest
+import yaml
+
+from realesrgan.data.realesrgan_dataset import RealESRGANDataset
+from realesrgan.data.realesrgan_paired_dataset import RealESRGANPairedDataset
+
+
+def test_realesrgan_dataset():
+
+    with open('tests/data/test_realesrgan_dataset.yml', mode='r') as f:
+        opt = yaml.load(f, Loader=yaml.FullLoader)
+
+    dataset = RealESRGANDataset(opt)
+    assert dataset.io_backend_opt['type'] == 'disk'  # io backend
+    assert len(dataset) == 2  # whether to read correct meta info
+    assert dataset.kernel_list == [
+        'iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'
+    ]  # correct initialization the degradation configurations
+    assert dataset.betag_range2 == [0.5, 4]
+
+    # test __getitem__
+    result = dataset.__getitem__(0)
+    # check returned keys
+    expected_keys = ['gt', 'kernel1', 'kernel2', 'sinc_kernel', 'gt_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 400, 400)
+    assert result['kernel1'].shape == (21, 21)
+    assert result['kernel2'].shape == (21, 21)
+    assert result['sinc_kernel'].shape == (21, 21)
+    assert result['gt_path'] == 'tests/data/gt/baboon.png'
+
+    # ------------------ test lmdb backend -------------------- #
+    opt['dataroot_gt'] = 'tests/data/gt.lmdb'
+    opt['io_backend']['type'] = 'lmdb'
+
+    dataset = RealESRGANDataset(opt)
+    assert dataset.io_backend_opt['type'] == 'lmdb'  # io backend
+    assert len(dataset.paths) == 2  # whether to read correct meta info
+    assert dataset.kernel_list == [
+        'iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'
+    ]  # correct initialization the degradation configurations
+    assert dataset.betag_range2 == [0.5, 4]
+
+    # test __getitem__
+    result = dataset.__getitem__(1)
+    # check returned keys
+    expected_keys = ['gt', 'kernel1', 'kernel2', 'sinc_kernel', 'gt_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 400, 400)
+    assert result['kernel1'].shape == (21, 21)
+    assert result['kernel2'].shape == (21, 21)
+    assert result['sinc_kernel'].shape == (21, 21)
+    assert result['gt_path'] == 'comic'
+
+    # ------------------ test with sinc_prob = 0 -------------------- #
+    opt['dataroot_gt'] = 'tests/data/gt.lmdb'
+    opt['io_backend']['type'] = 'lmdb'
+    opt['sinc_prob'] = 0
+    opt['sinc_prob2'] = 0
+    opt['final_sinc_prob'] = 0
+    dataset = RealESRGANDataset(opt)
+    result = dataset.__getitem__(0)
+    # check returned keys
+    expected_keys = ['gt', 'kernel1', 'kernel2', 'sinc_kernel', 'gt_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 400, 400)
+    assert result['kernel1'].shape == (21, 21)
+    assert result['kernel2'].shape == (21, 21)
+    assert result['sinc_kernel'].shape == (21, 21)
+    assert result['gt_path'] == 'baboon'
+
+    # ------------------ lmdb backend should have paths ends with lmdb -------------------- #
+    with pytest.raises(ValueError):
+        opt['dataroot_gt'] = 'tests/data/gt'
+        opt['io_backend']['type'] = 'lmdb'
+        dataset = RealESRGANDataset(opt)
+
+
+def test_realesrgan_paired_dataset():
+
+    with open('tests/data/test_realesrgan_paired_dataset.yml', mode='r') as f:
+        opt = yaml.load(f, Loader=yaml.FullLoader)
+
+    dataset = RealESRGANPairedDataset(opt)
+    assert dataset.io_backend_opt['type'] == 'disk'  # io backend
+    assert len(dataset) == 2  # whether to read correct meta info
+
+    # test __getitem__
+    result = dataset.__getitem__(0)
+    # check returned keys
+    expected_keys = ['gt', 'lq', 'gt_path', 'lq_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 128, 128)
+    assert result['lq'].shape == (3, 32, 32)
+    assert result['gt_path'] == 'tests/data/gt/baboon.png'
+    assert result['lq_path'] == 'tests/data/lq/baboon.png'
+
+    # ------------------ test lmdb backend -------------------- #
+    opt['dataroot_gt'] = 'tests/data/gt.lmdb'
+    opt['dataroot_lq'] = 'tests/data/lq.lmdb'
+    opt['io_backend']['type'] = 'lmdb'
+
+    dataset = RealESRGANPairedDataset(opt)
+    assert dataset.io_backend_opt['type'] == 'lmdb'  # io backend
+    assert len(dataset) == 2  # whether to read correct meta info
+
+    # test __getitem__
+    result = dataset.__getitem__(1)
+    # check returned keys
+    expected_keys = ['gt', 'lq', 'gt_path', 'lq_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 128, 128)
+    assert result['lq'].shape == (3, 32, 32)
+    assert result['gt_path'] == 'comic'
+    assert result['lq_path'] == 'comic'
+
+    # ------------------ test paired_paths_from_folder -------------------- #
+    opt['dataroot_gt'] = 'tests/data/gt'
+    opt['dataroot_lq'] = 'tests/data/lq'
+    opt['io_backend'] = dict(type='disk')
+    opt['meta_info'] = None
+
+    dataset = RealESRGANPairedDataset(opt)
+    assert dataset.io_backend_opt['type'] == 'disk'  # io backend
+    assert len(dataset) == 2  # whether to read correct meta info
+
+    # test __getitem__
+    result = dataset.__getitem__(0)
+    # check returned keys
+    expected_keys = ['gt', 'lq', 'gt_path', 'lq_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 128, 128)
+    assert result['lq'].shape == (3, 32, 32)
+
+    # ------------------ test normalization -------------------- #
+    dataset.mean = [0.5, 0.5, 0.5]
+    dataset.std = [0.5, 0.5, 0.5]
+    # test __getitem__
+    result = dataset.__getitem__(0)
+    # check returned keys
+    expected_keys = ['gt', 'lq', 'gt_path', 'lq_path']
+    assert set(expected_keys).issubset(set(result.keys()))
+    # check shape and contents
+    assert result['gt'].shape == (3, 128, 128)
+    assert result['lq'].shape == (3, 32, 32)

tests/test_discriminator_arch.py

@@ -0,0 +1,19 @@
+import torch
+
+from realesrgan.archs.discriminator_arch import UNetDiscriminatorSN
+
+
+def test_unetdiscriminatorsn():
+    """Test arch: UNetDiscriminatorSN."""
+
+    # model init and forward (cpu)
+    net = UNetDiscriminatorSN(num_in_ch=3, num_feat=4, skip_connection=True)
+    img = torch.rand((1, 3, 32, 32), dtype=torch.float32)
+    output = net(img)
+    assert output.shape == (1, 1, 32, 32)
+
+    # model init and forward (gpu)
+    if torch.cuda.is_available():
+        net.cuda()
+        output = net(img.cuda())
+        assert output.shape == (1, 1, 32, 32)

tests/test_model.py

@@ -0,0 +1,126 @@
+import torch
+import yaml
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.data.paired_image_dataset import PairedImageDataset
+from basicsr.losses.losses import GANLoss, L1Loss, PerceptualLoss
+
+from realesrgan.archs.discriminator_arch import UNetDiscriminatorSN
+from realesrgan.models.realesrgan_model import RealESRGANModel
+from realesrgan.models.realesrnet_model import RealESRNetModel
+
+
+def test_realesrnet_model():
+    with open('tests/data/test_realesrnet_model.yml', mode='r') as f:
+        opt = yaml.load(f, Loader=yaml.FullLoader)
+
+    # build model
+    model = RealESRNetModel(opt)
+    # test attributes
+    assert model.__class__.__name__ == 'RealESRNetModel'
+    assert isinstance(model.net_g, RRDBNet)
+    assert isinstance(model.cri_pix, L1Loss)
+    assert isinstance(model.optimizers[0], torch.optim.Adam)
+
+    # prepare data
+    gt = torch.rand((1, 3, 32, 32), dtype=torch.float32)
+    kernel1 = torch.rand((1, 5, 5), dtype=torch.float32)
+    kernel2 = torch.rand((1, 5, 5), dtype=torch.float32)
+    sinc_kernel = torch.rand((1, 5, 5), dtype=torch.float32)
+    data = dict(gt=gt, kernel1=kernel1, kernel2=kernel2, sinc_kernel=sinc_kernel)
+    model.feed_data(data)
+    # check dequeue
+    model.feed_data(data)
+    # check data shape
+    assert model.lq.shape == (1, 3, 8, 8)
+    assert model.gt.shape == (1, 3, 32, 32)
+
+    # change probability to test if-else
+    model.opt['gaussian_noise_prob'] = 0
+    model.opt['gray_noise_prob'] = 0
+    model.opt['second_blur_prob'] = 0
+    model.opt['gaussian_noise_prob2'] = 0
+    model.opt['gray_noise_prob2'] = 0
+    model.feed_data(data)
+    # check data shape
+    assert model.lq.shape == (1, 3, 8, 8)
+    assert model.gt.shape == (1, 3, 32, 32)
+
+    # ----------------- test nondist_validation -------------------- #
+    # construct dataloader
+    dataset_opt = dict(
+        name='Demo',
+        dataroot_gt='tests/data/gt',
+        dataroot_lq='tests/data/lq',
+        io_backend=dict(type='disk'),
+        scale=4,
+        phase='val')
+    dataset = PairedImageDataset(dataset_opt)
+    dataloader = torch.utils.data.DataLoader(dataset=dataset, batch_size=1, shuffle=False, num_workers=0)
+    assert model.is_train is True
+    model.nondist_validation(dataloader, 1, None, False)
+    assert model.is_train is True
+
+
+def test_realesrgan_model():
+    with open('tests/data/test_realesrgan_model.yml', mode='r') as f:
+        opt = yaml.load(f, Loader=yaml.FullLoader)
+
+    # build model
+    model = RealESRGANModel(opt)
+    # test attributes
+    assert model.__class__.__name__ == 'RealESRGANModel'
+    assert isinstance(model.net_g, RRDBNet)  # generator
+    assert isinstance(model.net_d, UNetDiscriminatorSN)  # discriminator
+    assert isinstance(model.cri_pix, L1Loss)
+    assert isinstance(model.cri_perceptual, PerceptualLoss)
+    assert isinstance(model.cri_gan, GANLoss)
+    assert isinstance(model.optimizers[0], torch.optim.Adam)
+    assert isinstance(model.optimizers[1], torch.optim.Adam)
+
+    # prepare data
+    gt = torch.rand((1, 3, 32, 32), dtype=torch.float32)
+    kernel1 = torch.rand((1, 5, 5), dtype=torch.float32)
+    kernel2 = torch.rand((1, 5, 5), dtype=torch.float32)
+    sinc_kernel = torch.rand((1, 5, 5), dtype=torch.float32)
+    data = dict(gt=gt, kernel1=kernel1, kernel2=kernel2, sinc_kernel=sinc_kernel)
+    model.feed_data(data)
+    # check dequeue
+    model.feed_data(data)
+    # check data shape
+    assert model.lq.shape == (1, 3, 8, 8)
+    assert model.gt.shape == (1, 3, 32, 32)
+
+    # change probability to test if-else
+    model.opt['gaussian_noise_prob'] = 0
+    model.opt['gray_noise_prob'] = 0
+    model.opt['second_blur_prob'] = 0
+    model.opt['gaussian_noise_prob2'] = 0
+    model.opt['gray_noise_prob2'] = 0
+    model.feed_data(data)
+    # check data shape
+    assert model.lq.shape == (1, 3, 8, 8)
+    assert model.gt.shape == (1, 3, 32, 32)
+
+    # ----------------- test nondist_validation -------------------- #
+    # construct dataloader
+    dataset_opt = dict(
+        name='Demo',
+        dataroot_gt='tests/data/gt',
+        dataroot_lq='tests/data/lq',
+        io_backend=dict(type='disk'),
+        scale=4,
+        phase='val')
+    dataset = PairedImageDataset(dataset_opt)
+    dataloader = torch.utils.data.DataLoader(dataset=dataset, batch_size=1, shuffle=False, num_workers=0)
+    assert model.is_train is True
+    model.nondist_validation(dataloader, 1, None, False)
+    assert model.is_train is True
+
+    # ----------------- test optimize_parameters -------------------- #
+    model.feed_data(data)
+    model.optimize_parameters(1)
+    assert model.output.shape == (1, 3, 32, 32)
+    assert isinstance(model.log_dict, dict)
+    # check returned keys
+    expected_keys = ['l_g_pix', 'l_g_percep', 'l_g_gan', 'l_d_real', 'out_d_real', 'l_d_fake', 'out_d_fake']
+    assert set(expected_keys).issubset(set(model.log_dict.keys()))

tests/test_utils.py

@@ -0,0 +1,87 @@
+import numpy as np
+from basicsr.archs.rrdbnet_arch import RRDBNet
+
+from realesrgan.utils import RealESRGANer
+
+
+def test_realesrganer():
+    # initialize with default model
+    restorer = RealESRGANer(
+        scale=4,
+        model_path='experiments/pretrained_models/RealESRGAN_x4plus.pth',
+        model=None,
+        tile=10,
+        tile_pad=10,
+        pre_pad=2,
+        half=False)
+    assert isinstance(restorer.model, RRDBNet)
+    assert restorer.half is False
+    # initialize with user-defined model
+    model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+    restorer = RealESRGANer(
+        scale=4,
+        model_path='experiments/pretrained_models/RealESRGAN_x4plus_anime_6B.pth',
+        model=model,
+        tile=10,
+        tile_pad=10,
+        pre_pad=2,
+        half=True)
+    # test attribute
+    assert isinstance(restorer.model, RRDBNet)
+    assert restorer.half is True
+
+    # ------------------ test pre_process ---------------- #
+    img = np.random.random((12, 12, 3)).astype(np.float32)
+    restorer.pre_process(img)
+    assert restorer.img.shape == (1, 3, 14, 14)
+    # with modcrop
+    restorer.scale = 1
+    restorer.pre_process(img)
+    assert restorer.img.shape == (1, 3, 16, 16)
+
+    # ------------------ test process ---------------- #
+    restorer.process()
+    assert restorer.output.shape == (1, 3, 64, 64)
+
+    # ------------------ test post_process ---------------- #
+    restorer.mod_scale = 4
+    output = restorer.post_process()
+    assert output.shape == (1, 3, 60, 60)
+
+    # ------------------ test tile_process ---------------- #
+    restorer.scale = 4
+    img = np.random.random((12, 12, 3)).astype(np.float32)
+    restorer.pre_process(img)
+    restorer.tile_process()
+    assert restorer.output.shape == (1, 3, 64, 64)
+
+    # ------------------ test enhance ---------------- #
+    img = np.random.random((12, 12, 3)).astype(np.float32)
+    result = restorer.enhance(img, outscale=2)
+    assert result[0].shape == (24, 24, 3)
+    assert result[1] == 'RGB'
+
+    # ------------------ test enhance with 16-bit image---------------- #
+    img = np.random.random((4, 4, 3)).astype(np.uint16) + 512
+    result = restorer.enhance(img, outscale=2)
+    assert result[0].shape == (8, 8, 3)
+    assert result[1] == 'RGB'
+
+    # ------------------ test enhance with gray image---------------- #
+    img = np.random.random((4, 4)).astype(np.float32)
+    result = restorer.enhance(img, outscale=2)
+    assert result[0].shape == (8, 8)
+    assert result[1] == 'L'
+
+    # ------------------ test enhance with RGBA---------------- #
+    img = np.random.random((4, 4, 4)).astype(np.float32)
+    result = restorer.enhance(img, outscale=2)
+    assert result[0].shape == (8, 8, 4)
+    assert result[1] == 'RGBA'
+
+    # ------------------ test enhance with RGBA, alpha_upsampler---------------- #
+    restorer.tile_size = 0
+    img = np.random.random((4, 4, 4)).astype(np.float32)
+    result = restorer.enhance(img, outscale=2, alpha_upsampler=None)
+    assert result[0].shape == (8, 8, 4)
+    assert result[1] == 'RGBA'