V0.2.3.0: add anime video models

Update readme for anime video models; add video demo (#181 )
* update readme * update readme * update readme * update readme * update readme * update readme * update readme * update readme * update readme
2021-12-12 20:19:09 +08:00 · 2021-12-12 20:17:30 +08:00 · 2021-12-12 16:49:35 +08:00 · 2021-12-12 13:29:21 +08:00 · 2021-12-09 17:41:19 +08:00 · 2021-11-28 19:54:19 +08:00
60 changed files with 2488 additions and 179 deletions
--- a/.github/workflows/no-response.yml
+++ b/.github/workflows/no-response.yml
@@ -1,12 +1,11 @@
 name: No Response

+# TODO: it seems not to work
 # 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.
+# **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:
--- a/.github/workflows/publish-pip.yml
+++ b/.github/workflows/publish-pip.yml
@@ -20,12 +20,13 @@ jobs:
      - name: Install dependencies
        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
+        run: python setup.py sdist bdist_wheel
      - name: Publish distribution to PyPI
        uses: pypa/gh-action-pypi-publish@master
        with:
--- a/.github/workflows/pylint.yml
+++ b/.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
--- a/.pre-commit-config.yaml
+++ b/.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
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -0,0 +1,41 @@
+# Contributing to Real-ESRGAN
+
+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:
--- a/FAQ.md
+++ b/FAQ.md
@@ -1,9 +1,5 @@
 # FAQ

-1. **What is the difference of `--netscale` and `outscale`?**
-
-A: TODO.
-
 1. **How to select models?**

 A: TODO.
--- a/README.md
+++ b/README.md
@@ -2,37 +2,55 @@

 [![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)

+[English](README.md) **|** [简体中文](README_CN.md)
+
+:fire: :fire: :fire: Add **small video models** for anime videos (**针对动漫视频的小模型**). Please see [anime video models](docs/anime_video_model.md).
+
 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>.
-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).
+2. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#Portable-executable-files). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).

 Real-ESRGAN aims at developing **Practical Algorithms for General Image 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).
+:art: Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, *etc*. See [CONTRIBUTING.md](CONTRIBUTING.md). All contributors are list [here](README.md#hugs-acknowledgement).
+
+:question: Frequently Asked Questions can be found in [FAQ.md](FAQ.md) (Well, it is still empty there =-=||).
+
+:milky_way: Thanks for your valuable feedbacks/suggestions. All the feedbacks are updated in [feedback.md](feedback.md).

 :triangular_flag_on_post: **Updates**
+- :white_check_mark: Add small models for anime videos. More details are in [anime video models](docs/anime_video_model.md).
+- :white_check_mark: Add the ncnn implementation [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
+- :white_check_mark: 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)
+- :white_check_mark: Support finetuning on your own data or paired data (*i.e.*, finetuning ESRGAN). See [here](Training.md#Finetune-Real-ESRGAN-on-your-own-dataset)
 - :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: 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)
 - :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)
+---
+
+If Real-ESRGAN is helpful in your photos/projects, please help to :star: this repo or recommend it to your friends. Thanks:blush: <br>
+Other recommended projects:<br>
+:arrow_forward: [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>
+:arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>
+:arrow_forward: [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>
+:arrow_forward: [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison. <br>

 ---

 ### :book: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

-> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [Project Page] &emsp; [Demo] <br>
+> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [Project Page] &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>
-> Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
+> Tencent ARC Lab; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

 <p align="center">
  <img src="assets/teaser.jpg">
@@ -52,7 +70,7 @@ Here is a TODO list in the near future:

 - [ ] optimize for human faces
 - [ ] optimize for texts
- [ ] optimize for anime images [in progress]
+- [x] optimize for anime images
 - [ ] support more scales
 - [ ] support controllable restoration strength

@@ -63,24 +81,48 @@ If you have some images that Real-ESRGAN could not well restored, please also op

 ### Portable executable files

-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**.
+You can download [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-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
+./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n model_name
 ```

-We have provided three models:
+We have provided five models:

 1. realesrgan-x4plus  (default)
 2. realesrnet-x4plus
-3. esrgan-x4
+3. realesrgan-x4plus-anime (optimized for anime images, small model size)
+4. RealESRGANv2-animevideo-xsx2 (anime video, X2)
+5. RealESRGANv2-animevideo-xsx4 (anime video, 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`

+### Usage of 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
+  -v                   verbose output
+  -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 (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 pre-trained models(default=models)
+  -n model-name        model name (default=realesrgan-x4plus, can be realesrgan-x4plus | realesrgan-x4plus-anime | realesrnet-x4plus)
+  -g gpu-id            gpu device to use (default=0) 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)
+```
+
 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).
@@ -116,9 +158,9 @@ This executable file is based on the wonderful [Tencent/ncnn](https://github.com

 ## :zap: Quick Inference

-Download pre-trained models: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
+### Inference general images

-Download pretrained models:
+Download pre-trained models: [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 experiments/pretrained_models
@@ -127,31 +169,76 @@ wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_
 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

+### Inference anime images
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+
+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)
+
+```bash
+# download model
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P experiments/pretrained_models
+# inference
+python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
+```
+
+Results are in the `results` folder
+
+### 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 --half --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
+  --half               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: Model Zoo

- [RealESRGAN-x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
- [RealESRNet-x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth)
- [RealESRGAN-x2plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth)
- [official ESRGAN-x4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth)
+Please see [docs/model_zoo.md](docs/model_zoo.md)

-## :computer: Training
+## :computer: Training and Finetuning on your own dataset

 A detailed guide can be found in [Training.md](Training.md).

 ## BibTeX

-    @Article{wang2021realesrgan,
-        title={Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
+    @InProceedings{wang2021realesrgan,
        author    = {Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
-        journal={arXiv:2107.10833},
-        year={2021}
+        title     = {Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
+        booktitle = {International Conference on Computer Vision Workshops (ICCVW)},
+        date      = {2021}
    }

 ## :e-mail: Contact

 If you have any question, please email `xintao.wang@outlook.com` or `xintaowang@tencent.com`.
+
+## :hugs: 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).
--- a/README_CN.md
+++ b/README_CN.md
@@ -0,0 +1,241 @@
+# Real-ESRGAN
+
+[![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)
+
+[English](README.md) **|** [简体中文](README_CN.md)
+
+:fire: :fire: :fire: 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.
+
+1. Real-ESRGAN的[Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) <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>.
+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/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [macOS版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-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](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](feedback.md)。
+
+:question: 常见的问题可以在[FAQ.md](FAQ.md)中找到答案。（好吧，现在还是空白的=-=||）
+
+:triangular_flag_on_post: **更新**
+- :white_check_mark: 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.
+- :white_check_mark: 添加了ncnn 实现：[Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
+- :white_check_mark: 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)
+- :white_check_mark: 支持用户在自己的数据上进行微调 (finetune)：[详情](Training.md#Finetune-Real-ESRGAN-on-your-own-dataset)
+- :white_check_mark: 支持使用[GFPGAN](https://github.com/TencentARC/GFPGAN)**增强人脸**
+- :white_check_mark: 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)
+- :white_check_mark: 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
+- :white_check_mark: [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.
+- :white_check_mark: 训练代码已经发布，具体做法可查看：[Training.md](Training.md)。
+
+---
+
+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>
+
+---
+
+### :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/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [macOS版](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-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. RealESRGANv2-animevideo-xsx2 (针对动漫视频, X2)
+5. RealESRGANv2-animevideo-xsx4 (针对动漫视频, X4)
+
+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
+  -v                   verbose output
+  -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 (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 pre-trained models(default=models)
+  -n model-name        model name (default=realesrgan-x4plus, can be realesrgan-x4plus | realesrgan-x4plus-anime | realesrnet-x4plus)
+  -g gpu-id            gpu device to use (default=0) 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)
+```
+
+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）
+
+这些exe文件均基于[Tencent/ncnn](https://github.com/Tencent/ncnn)以及[nihui](https://github.com/nihui)的[realsr-ncnn-vulkan](https://github.com/nihui/realsr-ncnn-vulkan)，感谢！
+
+---
+
+## :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 experiments/pretrained_models
+```
+
+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 experiments/pretrained_models
+# 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 --half --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
+  --half               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](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).
--- a/Training.md
+++ b/Training.md
@@ -1,16 +1,24 @@
-# :computer: How to Train Real-ESRGAN
+# :computer: How to Train/Finetune 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.
+- [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)

-## Overview
+## 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
+### Dataset Preparation

 We use DF2K (DIV2K and Flickr2K) + OST datasets for our training. Only HR images are required. <br>
 You can download from :
@@ -19,9 +27,30 @@ You can download from :
 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.
+Here are steps for data preparation.

-We then crop DF2K images into sub-images for faster IO and processing.
+#### 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):

@@ -32,7 +61,14 @@ DF2K_HR_sub/000001_s003.png
 ...
 ```

-## Train Real-ESRNet
+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
@@ -78,13 +114,23 @@ DF2K_HR_sub/000001_s003.png
    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 Real-ESRGAN
+    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.
@@ -93,8 +139,131 @@ DF2K_HR_sub/000001_s003.png
    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 trainig.
+
+**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 the root path of your folder
+    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
+```
--- a/2
+++ b/2
@@ -1 +1 @@
-0.2.2.2
+0.2.3.0
--- a/docs/anime_model.md
+++ b/docs/anime_model.md
@@ -0,0 +1,69 @@
+# 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.
+
+- [Anime Model](#anime-model)
+  - [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 experiments/pretrained_models
+# 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/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-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
--- a/docs/anime_video_model.md
+++ b/docs/anime_video_model.md
@@ -0,0 +1,121 @@
+# Anime Video Models
+
+:white_check_mark: We add small models that are optimized for anime videos :-)
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [RealESRGANv2-animevideo-xsx2](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/RealESRGANv2-animevideo-xsx2.pth) | X2    | Anime video model with XS size |
+| [RealESRGANv2-animevideo-xsx4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/RealESRGANv2-animevideo-xsx4.pth) | X4    | Anime video model with XS size |
+
+- [Anime Video Models](#anime-video-models)
+  - [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)
+
+---
+
+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/17445847/145707046-8702a17c-a194-4471-8a53-a4cc44c9594c.MP4
+
+## How to Use
+
+### PyTorch Inference
+
+```bash
+# download model
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/RealESRGANv2-animevideo-xsx2.pth -P experiments/pretrained_models
+# inference
+python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n RealESRGANv2-animevideo-xsx2 -s 2 -v -a --half --suffix outx2
+```
+
+### 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/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/realesrgan-ncnn-vulkan-20211212-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 RealESRGANv2-animevideo-xsx2 -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 -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 -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/17445847/145706827-384108c0-78f6-4aa7-9621-99d1aaf65682.mp4
+
+**More comparisons**
+
+https://user-images.githubusercontent.com/17445847/145707458-04a5e9b9-2edd-4d1f-b400-380a72e5f5e6.MP4
--- a/docs/model_zoo.md
+++ b/docs/model_zoo.md
@@ -0,0 +1,47 @@
+# :european_castle: Model Zoo
+
+- [:european_castle: Model Zoo](#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                        |
+
+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
+
+| 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 Anime Videos
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [RealESRGANv2-animevideo-xsx2](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/RealESRGANv2-animevideo-xsx2.pth) | X2    | Anime video model with XS size |
+| [RealESRGANv2-animevideo-xsx4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.3.0/RealESRGANv2-animevideo-xsx4.pth) | X4    | Anime video model with XS size |
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+TODO
--- a/docs/ncnn_conversion.md
+++ b/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`
--- a/feedback.md
+++ b/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).
--- a/inference_realesrgan.py
+++ b/inference_realesrgan.py
@@ -2,23 +2,29 @@ import argparse
 import cv2
 import glob
 import os
+from basicsr.archs.rrdbnet_arch import RRDBNet

 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',
-        help='Path to the pre-trained model')
-    parser.add_argument('--output', type=str, default='results', help='Output folder')
-    parser.add_argument('--netscale', type=int, default=4, help='Upsample scale factor of the network')
-    parser.add_argument('--outscale', type=float, default=4, help='The final upsampling scale of the image')
+        default='RealESRGAN_x4plus',
+        help=('Model names: RealESRGAN_x4plus | RealESRNet_x4plus | RealESRGAN_x4plus_anime_6B | RealESRGAN_x2plus'
+              'RealESRGANv2-anime-xsx2 | RealESRGANv2-animevideo-xsx2-nousm | RealESRGANv2-animevideo-xsx2'
+              'RealESRGANv2-anime-xsx4 | RealESRGANv2-animevideo-xsx4-nousm | RealESRGANv2-animevideo-xsx4'))
+    parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
+    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 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')
@@ -35,15 +41,46 @@ def main():
        help='Image extension. Options: auto | jpg | png, auto means using the same extension as inputs')
    args = parser.parse_args()

+    # determine models according to model names
+    args.model_name = args.model_name.split('.')[0]
+    if args.model_name in ['RealESRGAN_x4plus', '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
+    elif args.model_name in ['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
+    elif args.model_name in ['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
+    elif args.model_name in [
+            'RealESRGANv2-anime-xsx2', 'RealESRGANv2-animevideo-xsx2-nousm', 'RealESRGANv2-animevideo-xsx2'
+    ]:  # x2 VGG-style model (XS size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=2, act_type='prelu')
+        netscale = 2
+    elif args.model_name in [
+            'RealESRGANv2-anime-xsx4', 'RealESRGANv2-animevideo-xsx4-nousm', 'RealESRGANv2-animevideo-xsx4'
+    ]:  # 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
+
+    # determine model paths
+    model_path = os.path.join('experiments/pretrained_models', args.model_name + '.pth')
+    if not os.path.isfile(model_path):
+        model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
+    if not os.path.isfile(model_path):
+        raise ValueError(f'Model {args.model_name} does not exist.')
+
+    # restorer
    upsampler = RealESRGANer(
-        scale=args.netscale,
-        model_path=args.model_path,
+        scale=netscale,
+        model_path=model_path,
+        model=model,
        tile=args.tile,
        tile_pad=args.tile_pad,
        pre_pad=args.pre_pad,
        half=args.half)

-    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',
@@ -68,20 +105,12 @@ 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:
--- a/inference_realesrgan_video.py
+++ b/inference_realesrgan_video.py
@@ -0,0 +1,199 @@
+import argparse
+import glob
+import mimetypes
+import os
+import queue
+import shutil
+import torch
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.logger import AvgTimer
+from tqdm import tqdm
+
+from realesrgan import IOConsumer, PrefetchReader, RealESRGANer
+from realesrgan.archs.srvgg_arch import SRVGGNetCompact
+
+
+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 image or folder')
+    parser.add_argument(
+        '-n',
+        '--model_name',
+        type=str,
+        default='RealESRGAN_x4plus',
+        help=('Model names: RealESRGAN_x4plus | RealESRNet_x4plus | RealESRGAN_x4plus_anime_6B | RealESRGAN_x2plus'
+              'RealESRGANv2-anime-xsx2 | RealESRGANv2-animevideo-xsx2-nousm | RealESRGANv2-animevideo-xsx2'
+              'RealESRGANv2-anime-xsx4 | RealESRGANv2-animevideo-xsx4-nousm | RealESRGANv2-animevideo-xsx4'))
+    parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
+    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('--half', action='store_true', help='Use half precision during inference')
+    parser.add_argument('-v', '--video', action='store_true', help='Output a video using ffmpeg')
+    parser.add_argument('-a', '--audio', action='store_true', help='Keep audio')
+    parser.add_argument('--fps', type=float, default=None, help='FPS of the output video')
+    parser.add_argument('--consumer', type=int, default=4, help='Number of IO consumers')
+
+    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()
+
+    # ---------------------- determine models according to model names ---------------------- #
+    args.model_name = args.model_name.split('.')[0]
+    if args.model_name in ['RealESRGAN_x4plus', '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
+    elif args.model_name in ['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
+    elif args.model_name in ['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
+    elif args.model_name in [
+            'RealESRGANv2-anime-xsx2', 'RealESRGANv2-animevideo-xsx2-nousm', 'RealESRGANv2-animevideo-xsx2'
+    ]:  # x2 VGG-style model (XS size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=2, act_type='prelu')
+        netscale = 2
+    elif args.model_name in [
+            'RealESRGANv2-anime-xsx4', 'RealESRGANv2-animevideo-xsx4-nousm', 'RealESRGANv2-animevideo-xsx4'
+    ]:  # 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
+
+    # ---------------------- determine model paths ---------------------- #
+    model_path = os.path.join('experiments/pretrained_models', args.model_name + '.pth')
+    if not os.path.isfile(model_path):
+        model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
+    if not os.path.isfile(model_path):
+        raise ValueError(f'Model {args.model_name} does not exist.')
+
+    # restorer
+    upsampler = RealESRGANer(
+        scale=netscale,
+        model_path=model_path,
+        model=model,
+        tile=args.tile,
+        tile_pad=args.tile_pad,
+        pre_pad=args.pre_pad,
+        half=args.half)
+
+    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',
+            upscale=args.outscale,
+            arch='clean',
+            channel_multiplier=2,
+            bg_upsampler=upsampler)
+    os.makedirs(args.output, exist_ok=True)
+    # for saving restored frames
+    save_frame_folder = os.path.join(args.output, 'frames_tmpout')
+    os.makedirs(save_frame_folder, exist_ok=True)
+
+    if mimetypes.guess_type(args.input)[0].startswith('video'):  # is a video file
+        video_name = os.path.splitext(os.path.basename(args.input))[0]
+        frame_folder = os.path.join('tmp_frames', video_name)
+        os.makedirs(frame_folder, exist_ok=True)
+        # use ffmpeg to extract frames
+        os.system(f'ffmpeg -i {args.input} -qscale:v 1 -qmin 1 -qmax 1 -vsync 0  {frame_folder}/frame%08d.png')
+        # get image path list
+        paths = sorted(glob.glob(os.path.join(frame_folder, '*')))
+        if args.video:
+            if args.fps is None:
+                # get input video fps
+                import ffmpeg
+                probe = ffmpeg.probe(args.input)
+                video_streams = [stream for stream in probe['streams'] if stream['codec_type'] == 'video']
+                args.fps = eval(video_streams[0]['avg_frame_rate'])
+    elif mimetypes.guess_type(args.input)[0].startswith('image'):  # is an image file
+        paths = [args.input]
+        video_name = 'video'
+    else:
+        paths = sorted(glob.glob(os.path.join(args.input, '*')))
+        video_name = 'video'
+
+    timer = AvgTimer()
+    timer.start()
+    pbar = tqdm(total=len(paths), unit='frame', desc='inference')
+    # set up prefetch reader
+    reader = PrefetchReader(paths, num_prefetch_queue=4)
+    reader.start()
+
+    que = queue.Queue()
+    consumers = [IOConsumer(args, que, f'IO_{i}') for i in range(args.consumer)]
+    for consumer in consumers:
+        consumer.start()
+
+    for idx, (path, img) in enumerate(zip(paths, reader)):
+        imgname, extension = os.path.splitext(os.path.basename(path))
+        if len(img.shape) == 3 and img.shape[2] == 4:
+            img_mode = 'RGBA'
+        else:
+            img_mode = None
+
+        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:
+            if args.ext == 'auto':
+                extension = extension[1:]
+            else:
+                extension = args.ext
+            if img_mode == 'RGBA':  # RGBA images should be saved in png format
+                extension = 'png'
+            save_path = os.path.join(save_frame_folder, f'{imgname}_out.{extension}')
+
+            que.put({'output': output, 'save_path': save_path})
+
+        pbar.update(1)
+        torch.cuda.synchronize()
+        timer.record()
+        avg_fps = 1. / (timer.get_avg_time() + 1e-7)
+        pbar.set_description(f'idx {idx}, fps {avg_fps:.2f}')
+
+    for _ in range(args.consumer):
+        que.put('quit')
+    for consumer in consumers:
+        consumer.join()
+    pbar.close()
+
+    # merge frames to video
+    if args.video:
+        video_save_path = os.path.join(args.output, f'{video_name}_{args.suffix}.mp4')
+        if args.audio:
+            os.system(
+                f'ffmpeg -r {args.fps} -i {save_frame_folder}/frame%08d_out.{extension} -i {args.input}'
+                f' -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r {args.fps} -pix_fmt yuv420p  {video_save_path}')
+        else:
+            os.system(f'ffmpeg -i {save_frame_folder}/frame%08d_out.{extension} '
+                      f'-c:v libx264 -r {args.fps} -pix_fmt yuv420p {video_save_path}')
+
+        # delete tmp file
+        shutil.rmtree(save_frame_folder)
+        if os.path.isdir(frame_folder):
+            shutil.rmtree(frame_folder)
+
+
+if __name__ == '__main__':
+    main()
--- a/inputs/video/onepiece_demo.mp4
+++ b/inputs/video/onepiece_demo.mp4
--- a/options/finetune_realesrgan_x4plus.yml
+++ b/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
--- a/options/finetune_realesrgan_x4plus_pairdata.yml
+++ b/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
--- a/options/train_realesrgan_x2plus.yml
+++ b/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
--- a/options/train_realesrgan_x4plus.yml
+++ b/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
--- a/options/train_realesrnet_x2plus.yml
+++ b/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
--- a/options/train_realesrnet_x4plus.yml
+++ b/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
--- a/realesrgan/init.py
+++ b/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 *
--- a/realesrgan/archs/discriminator_arch.py
+++ b/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
+        # extra convolutions
        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)
--- a/realesrgan/archs/srvgg_arch.py
+++ b/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
--- a/realesrgan/data/realesrgan_dataset.py
+++ b/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.betap_range = opt['betap_range']
-        self.sinc_prob = opt['sinc_prob']
+        self.betag_range = opt['betag_range']  # betag used in generalized Gaussian blur kernels
+        self.betap_range = opt['betap_range']  # betap used in plateau blur kernels
+        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)
--- a/realesrgan/data/realesrgan_paired_dataset.py
+++ b/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)
--- a/realesrgan/models/realesrgan_model.py
+++ b/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.usm_sharpener = USMSharp().cuda()
-        self.queue_size = opt['queue_size']
+        self.jpeger = DiffJPEG(differentiable=False).cuda()  # simulate JPEG compression artifacts
+        self.usm_sharpener = USMSharp().cuda()  # do usm sharpening
+        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
--- a/realesrgan/models/realesrnet_model.py
+++ b/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.usm_sharpener = USMSharp().cuda()
-        self.queue_size = opt['queue_size']
+        self.jpeger = DiffJPEG(differentiable=False).cuda()  # simulate JPEG compression artifacts
+        self.usm_sharpener = USMSharp().cuda()  # do usm sharpening
+        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
--- a/realesrgan/utils.py
+++ b/realesrgan/utils.py
@@ -2,18 +2,31 @@ import cv2
 import math
 import numpy as np
 import os
+import queue
+import threading
 import torch
-from basicsr.archs.rrdbnet_arch import RRDBNet
-from torch.hub import download_url_to_file, get_dir
+from basicsr.utils.download_util import load_file_from_url
 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, model=None, tile=0, tile_pad=10, pre_pad=10, half=False):
        self.scale = scale
        self.tile_size = tile
        self.tile_pad = tile_pad
@@ -23,12 +36,12 @@ class RealESRGANer():

        # initialize model
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=scale)
-
+        # if the model_path starts with https, it will first download models to the folder: realesrgan/weights
        if model_path.startswith('https://'):
            model_path = load_file_from_url(
-                url=model_path, model_dir='realesrgan/weights', progress=True, file_name=None)
-        loadnet = torch.load(model_path)
+                url=model_path, model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'), progress=True, file_name=None)
+        loadnet = torch.load(model_path, map_location=torch.device('cpu'))
+        # prefer to use params_ema
        if 'params_ema' in loadnet:
            keyname = 'params_ema'
        else:
@@ -40,6 +53,8 @@ class RealESRGANer():
            self.model = self.model.half()

    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 +63,7 @@ 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 +78,14 @@ 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 +125,7 @@ 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 +206,7 @@ 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 +230,51 @@ class RealESRGANer():
        return output, img_mode


-def load_file_from_url(url, model_dir=None, progress=True, file_name=None):
-    """Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py
+class PrefetchReader(threading.Thread):
+    """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)
-    filename = os.path.basename(parts.path)
-    if file_name is not None:
-        filename = file_name
-    cached_file = os.path.abspath(os.path.join(ROOT_DIR, model_dir, filename))
-    if not os.path.exists(cached_file):
-        print(f'Downloading: "{url}" to {cached_file}\n')
-        download_url_to_file(url, cached_file, hash_prefix=None, progress=progress)
-    return cached_file
+    def run(self):
+        for img_path in self.img_list:
+            img = cv2.imread(img_path, cv2.IMREAD_UNCHANGED)
+            self.que.put(img)
+
+        self.que.put(None)
+
+    def __next__(self):
+        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.')
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,3 +5,5 @@ numpy
 opencv-python
 Pillow
 torch>=1.7
+torchvision
+tqdm
--- a/scripts/extract_subimages.py
+++ b/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)
--- a/scripts/generate_meta_info.py
+++ b/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)
--- a/scripts/generate_meta_info_pairdata.py
+++ b/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)
--- a/scripts/generate_multiscale_DF2K.py
+++ b/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')
--- a/scripts/pytorch2onnx.py
+++ b/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'])
+
+def main(args):
+    # 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()

-# An example input you would normally provide to your model's forward() method
+    # An example input
    x = torch.rand(1, 3, 64, 64)
-
    # Export the model
    with torch.no_grad():
-    torch_out = torch.onnx._export(model, x, 'realesrgan-x4.onnx', opset_version=11, export_params=True)
+        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)
--- a/setup.cfg
+++ b/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/
--- a/setup.py
+++ b/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'

--- a/tests/data/gt.lmdb/data.mdb
+++ b/tests/data/gt.lmdb/data.mdb
--- a/tests/data/gt.lmdb/lock.mdb
+++ b/tests/data/gt.lmdb/lock.mdb
--- a/tests/data/gt.lmdb/meta_info.txt
+++ b/tests/data/gt.lmdb/meta_info.txt
@@ -0,0 +1,2 @@
+baboon.png (480,500,3) 1
+comic.png (360,240,3) 1
--- a/tests/data/gt/baboon.png
+++ b/tests/data/gt/baboon.png
--- a/tests/data/gt/comic.png
+++ b/tests/data/gt/comic.png
--- a/tests/data/lq.lmdb/data.mdb
+++ b/tests/data/lq.lmdb/data.mdb
--- a/tests/data/lq.lmdb/lock.mdb
+++ b/tests/data/lq.lmdb/lock.mdb
--- a/tests/data/lq.lmdb/meta_info.txt
+++ b/tests/data/lq.lmdb/meta_info.txt
@@ -0,0 +1,2 @@
+baboon.png (120,125,3) 1
+comic.png (80,60,3) 1
--- a/tests/data/lq/baboon.png
+++ b/tests/data/lq/baboon.png
--- a/tests/data/lq/comic.png
+++ b/tests/data/lq/comic.png
--- a/tests/data/meta_info_gt.txt
+++ b/tests/data/meta_info_gt.txt
@@ -0,0 +1,2 @@
+baboon.png
+comic.png
--- a/tests/data/meta_info_pair.txt
+++ b/tests/data/meta_info_pair.txt
@@ -0,0 +1,2 @@
+gt/baboon.png, lq/baboon.png
+gt/comic.png, lq/comic.png
--- a/tests/data/test_realesrgan_dataset.yml
+++ b/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
--- a/tests/data/test_realesrgan_model.yml
+++ b/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
--- a/tests/data/test_realesrgan_paired_dataset.yml
+++ b/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
--- a/tests/data/test_realesrnet_model.yml
+++ b/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
--- a/tests/test_dataset.py
+++ b/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)
--- a/tests/test_discriminator_arch.py
+++ b/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)
--- a/tests/test_model.py
+++ b/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()))
--- a/tests/test_utils.py
+++ b/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'
Author	SHA1	Message	Date
Xintao	f07aaffda0	V0.2.3.0: add anime video models	2021-12-12 20:19:09 +08:00
Xintao	20355e0c79	Update readme for anime video models; add video demo (#181 ) * update readme * update readme * update readme * update readme * update readme * update readme * update readme * update readme * update readme	2021-12-12 20:17:30 +08:00
Xintao	192f672f91	add inference_realesrgan_video	2021-12-12 16:49:35 +08:00
Xintao	696e1a6741	add SRVGGNetCompact arch, update inference	2021-12-12 13:29:21 +08:00
Xintao	3e0085aeda	V0.2.2.6	2021-12-09 17:41:19 +08:00
Xintao	42110857ef	add unittest for model and utils	2021-11-28 19:54:19 +08:00
Xintao	1d180efaf3	add unittest for dataset and archs	2021-11-28 15:59:14 +08:00
Xintao	7dd860a881	catch more specific errors	2021-11-24 00:14:05 +08:00
Xintao	35ee6f781e	improve codes comments	2021-11-23 00:52:00 +08:00
Xintao	c9023b3d7a	Update README_CN.md (#142 ) * update contribution * updte readme * updte readme * update readme-cn * update readme-cn * update readme-cn * update readme-cn * update readme-cn	2021-11-01 19:16:48 +08:00
Asiimoviet	fb79d65ff3	Added Chinese README (#126 ) * Added Chinese README * Update README_CN.md * Create README_CN.md	2021-11-01 17:00:06 +08:00
Xintao	3338b31f48	update setup.py, V0.2.2.5	2021-10-22 17:16:43 +08:00
Xintao	501efe3da6	update ReadMe	2021-10-17 01:33:45 +08:00
Xintao	8beb7ed17d	add feedback of anime models	2021-10-17 01:27:04 +08:00
Xintao	e2d30f9ea4	update readme: add usage guidance	2021-10-17 01:03:55 +08:00
Xintao	d715e3d26a	update readme	2021-10-16 23:30:57 +08:00
Xintao	772923e207	add codespell to pre-commit hook	2021-09-27 15:35:37 +08:00
Christian Clauss	14247a89d9	Fix typos discovered by codespell (#95 ) * Improve performance * !fixup Fix typo discovered by codespell * fixup! Fix typo discovered by codespell * fixup! Add codespell to lint process	2021-09-27 14:53:03 +08:00
Xintao	aa584e05bc	minor updates on Training.md	2021-09-17 10:30:52 +08:00
Xintao	b525d1793b	add trainining with one gpu	2021-09-17 10:13:25 +08:00
Xintao	0ad2e9c61e	set num_gpu to auto in options	2021-09-17 10:07:09 +08:00
Xintao	90ddf13b5e	Merge branch 'master' of github.com:xinntao/Real-ESRGAN	2021-09-07 21:28:03 +08:00
Xintao	8675208bc9	update: format and standard	2021-09-07 21:27:45 +08:00
Pratik Goyal	8f8536b6d1	Minor spelling correction (#67 )	2021-09-03 14:38:03 +08:00
Xintao	f83472d011	version 0.2.2.4	2021-09-01 00:19:21 +08:00
Xintao	e1b8832f1b	Update README for Real-ESRGAN-anime model (#62 ) * try to add video mp4 * update * update readme * update readme * update readme * update readme * update readme	2021-09-01 00:18:07 +08:00
Xintao	6ff747174d	adapt Real-ESRGAN-anime model	2021-08-31 22:28:30 +08:00
Xintao	c1669c4b0a	support model config during inference	2021-08-31 19:58:40 +08:00
Xintao	18a9c386a8	update readme	2021-08-30 00:02:27 +08:00
Xintao	b659608fb3	add contributing	2021-08-29 23:55:39 +08:00
Xintao	ee5f7b34cb	update open issues	2021-08-29 11:28:15 +08:00
Xintao	3ce826cabe	fix import bug in setup.py	2021-08-28 13:26:09 +08:00
Xintao	2c20a354b6	add check arg	2021-08-28 13:20:10 +08:00
Xintao	3e1f780f51	update readme	2021-08-27 16:25:38 +08:00
Xintao	f5ccd64ce5	support finetune with paired data	2021-08-27 16:14:48 +08:00
Xintao	194c2c14b3	updte readme	2021-08-26 23:12:00 +08:00
Xintao	0fcb49a299	add extract_subimages	2021-08-26 22:55:56 +08:00
Xintao	9976a34454	update pypi, version 0.2.2.3	2021-08-26 22:27:19 +08:00
@@ -1 +1 @@
 .2.2.2
 .2.3.0