Add Replicate demo (#428)

* add cog.yaml * add cog predict * add cog predict * update cog predict * update cog predict * add alpha png * update cog predict * update cog predict * update cog predict * update readme * fix codespell
2022-09-05 00:13:42 +08:00
parent e2db576020
commit e5763af574
7 changed files with 178 additions and 5 deletions
--- a/README.md
+++ b/README.md
@@ -21,7 +21,8 @@
 🔥 **AnimeVideo-v3 model (动漫视频小模型)**. Please see [[*anime video models*](docs/anime_video_model.md)] and [[*comparisons*](docs/anime_comparisons.md)]<br>
 🔥 **RealESRGAN_x4plus_anime_6B** for anime images **(动漫插图模型)**. Please see [[*anime_model*](docs/anime_model.md)]

-1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B)
+<!-- 1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B) -->
+1. :boom: **Add** online demo: [![Replicate](https://img.shields.io/static/v1?label=Demo&message=Replicate&color=blue)](https://replicate.com/xinntao/realesrgan).
 1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN **|** [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**)
 1. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#portable-executable-files-ncnn). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
 1. You can watch enhanced animations in [Tencent Video](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html). 欢迎观看[腾讯视频动漫修复](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html)
--- a/cog.yaml
+++ b/cog.yaml
@@ -0,0 +1,22 @@
+# This file is used for constructing replicate env
+image: "r8.im/tencentarc/realesrgan"
+
+build:
+  gpu: true
+  python_version: "3.8"
+  system_packages:
+    - "libgl1-mesa-glx"
+    - "libglib2.0-0"
+  python_packages:
+    - "torch==1.7.1"
+    - "torchvision==0.8.2"
+    - "numpy==1.21.1"
+    - "lmdb==1.2.1"
+    - "opencv-python==4.5.3.56"
+    - "PyYAML==5.4.1"
+    - "tqdm==4.62.2"
+    - "yapf==0.31.0"
+    - "basicsr==1.4.2"
+    - "facexlib==0.2.5"
+
+predict: "cog_predict.py:Predictor"
--- a/cog_predict.py
+++ b/cog_predict.py
@@ -0,0 +1,150 @@
+# flake8: noqa
+# This file is used for deploying replicate models
+# running: cog predict -i img=@inputs/00017_gray.png -i version='General - v3' -i scale=2 -i face_enhance=True -i tile=0
+# push: cog push r8.im/xinntao/realesrgan
+
+import os
+
+os.system('pip install gfpgan')
+os.system('python setup.py develop')
+
+import cv2
+import shutil
+import tempfile
+import torch
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.archs.srvgg_arch import SRVGGNetCompact
+
+from realesrgan.utils import RealESRGANer
+
+try:
+    from cog import BasePredictor, Input, Path
+    from gfpgan import GFPGANer
+except Exception:
+    print('please install cog and realesrgan package')
+
+
+class Predictor(BasePredictor):
+
+    def setup(self):
+        os.makedirs('output', exist_ok=True)
+        # download weights
+        if not os.path.exists('realesrgan/weights/realesr-general-x4v3.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P ./realesrgan/weights'
+            )
+        if not os.path.exists('realesrgan/weights/GFPGANv1.4.pth'):
+            os.system(
+                'wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P ./realesrgan/weights'
+            )
+        if not os.path.exists('realesrgan/weights/RealESRGAN_x4plus.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P ./realesrgan/weights'
+            )
+        if not os.path.exists('realesrgan/weights/RealESRGAN_x4plus_anime_6B.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P ./realesrgan/weights'
+            )
+        if not os.path.exists('realesrgan/weights/realesr-animevideov3.pth'):
+            os.system(
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P ./realesrgan/weights'
+            )
+
+    def choose_model(self, scale, version, tile=0):
+        half = True if torch.cuda.is_available() else False
+        if version == 'General - RealESRGANplus':
+            model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+            model_path = 'realesrgan/weights/RealESRGAN_x4plus.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'General - v3':
+            model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+            model_path = 'realesrgan/weights/realesr-general-x4v3.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'Anime - anime6B':
+            model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+            model_path = 'realesrgan/weights/RealESRGAN_x4plus_anime_6B.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+        elif version == 'AnimeVideo - v3':
+            model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
+            model_path = 'realesrgan/weights/realesr-animevideov3.pth'
+            self.upsampler = RealESRGANer(
+                scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
+
+        self.face_enhancer = GFPGANer(
+            model_path='realesrgan/weights/GFPGANv1.4.pth',
+            upscale=scale,
+            arch='clean',
+            channel_multiplier=2,
+            bg_upsampler=self.upsampler)
+
+    def predict(
+        self,
+        img: Path = Input(description='Input'),
+        version: str = Input(
+            description='RealESRGAN version. Please see [Readme] below for more descriptions',
+            choices=['General - RealESRGANplus', 'General - v3', 'Anime - anime6B', 'AnimeVideo - v3'],
+            default='General - v3'),
+        scale: float = Input(description='Rescaling factor', default=2),
+        face_enhance: bool = Input(
+            description='Enhance faces with GFPGAN. Note that it does not work for anime images/vidoes', default=False),
+        tile: int = Input(
+            description=
+            'Tile size. Default is 0, that is no tile. When encountering the out-of-GPU-memory issue, please specify it, e.g., 400 or 200',
+            default=0)
+    ) -> Path:
+        if tile <= 100 or tile is None:
+            tile = 0
+        print(f'img: {img}. version: {version}. scale: {scale}. face_enhance: {face_enhance}. tile: {tile}.')
+        try:
+            extension = os.path.splitext(os.path.basename(str(img)))[1]
+            img = cv2.imread(str(img), cv2.IMREAD_UNCHANGED)
+            if len(img.shape) == 3 and img.shape[2] == 4:
+                img_mode = 'RGBA'
+            elif len(img.shape) == 2:
+                img_mode = None
+                img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+            else:
+                img_mode = None
+
+            h, w = img.shape[0:2]
+            if h < 300:
+                img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
+
+            self.choose_model(scale, version, tile)
+
+            try:
+                if face_enhance:
+                    _, _, output = self.face_enhancer.enhance(
+                        img, has_aligned=False, only_center_face=False, paste_back=True)
+                else:
+                    output, _ = self.upsampler.enhance(img, outscale=scale)
+            except RuntimeError as error:
+                print('Error', error)
+                print('If you encounter CUDA out of memory, try to set "tile" to a smaller size, e.g., 400.')
+
+            if img_mode == 'RGBA':  # RGBA images should be saved in png format
+                extension = 'png'
+            # save_path = f'output/out.{extension}'
+            # cv2.imwrite(save_path, output)
+            out_path = Path(tempfile.mkdtemp()) / f'out.{extension}'
+            cv2.imwrite(str(out_path), output)
+        except Exception as error:
+            print('global exception: ', error)
+        finally:
+            clean_folder('output')
+        return out_path
+
+
+def clean_folder(folder):
+    for filename in os.listdir(folder):
+        file_path = os.path.join(folder, filename)
+        try:
+            if os.path.isfile(file_path) or os.path.islink(file_path):
+                os.unlink(file_path)
+            elif os.path.isdir(file_path):
+                shutil.rmtree(file_path)
+        except Exception as e:
+            print(f'Failed to delete {file_path}. Reason: {e}')
--- a/docs/Training.md
+++ b/docs/Training.md
@@ -166,7 +166,7 @@ You can finetune Real-ESRGAN on your own dataset. Typically, the fine-tuning pro

 ### 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.
+Only high-resolution images are required. The low-quality images are generated with the degradation process described in Real-ESRGAN during training.

 **1. Prepare dataset**

--- a/inputs/00017_gray.png
+++ b/inputs/00017_gray.png
--- a/inputs/children-alpha.png
+++ b/inputs/children-alpha.png
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,6 @@
-basicsr>=1.3.3.11
-facexlib>=0.2.0.3
-gfpgan>=0.2.1
+basicsr>=1.4.2
+facexlib>=0.2.5
+gfpgan>=1.3.5
 numpy
 opencv-python
 Pillow