Iniital commit

.gitignore

@@ -0,0 +1 @@
+.DS_Store

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.9-slim-bullseye
+
+RUN apt-get update
+RUN apt-get install git ffmpeg libsm6 libxext6 wget -y
+
+COPY requirements.txt .
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+RUN pip install gfpgan
+
+# Create working directory
+RUN mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# Copy model
+COPY gfpgan /usr/src/app/gfpgan
+
+# Copy source code
+COPY inference.py /usr/src/app
+
+ENTRYPOINT ["python3", "/usr/src/app/inference.py", "-i", "/in", "-o", "/out", "-s", "4"]

gfpgan/weights/GFPGANv1.3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c953a88f2727c85c3d9ae72e2bd4846bbaf59fe6972ad94130e23e7017524a70
+size 348632874

gfpgan/weights/detection_Resnet50_Final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1de9c2944f2ccddca5f5e010ea5ae64a39845a86311af6fdf30841b0a5a16d
+size 109497761

gfpgan/weights/parsing_parsenet.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d558d8d0e42c20224f13cf5a29c79eba2d59913419f945545d8cf7b72920de2
+size 85331193

inference.py

@@ -0,0 +1,174 @@
+import argparse
+import cv2
+import glob
+import numpy as np
+import os
+import torch
+from basicsr.utils import imwrite
+
+from gfpgan import GFPGANer
+
+
+def main():
+    """Inference demo for GFPGAN (for users).
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '-i',
+        '--input',
+        type=str,
+        default='inputs/whole_imgs',
+        help='Input image or folder. Default: inputs/whole_imgs')
+    parser.add_argument('-o', '--output', type=str, default='results', help='Output folder. Default: results')
+    # we use version to select models, which is more user-friendly
+    parser.add_argument(
+        '-v', '--version', type=str, default='1.3', help='GFPGAN model version. Option: 1 | 1.2 | 1.3. Default: 1.3')
+    parser.add_argument(
+        '-s', '--upscale', type=int, default=2, help='The final upsampling scale of the image. Default: 2')
+
+    parser.add_argument(
+        '--bg_upsampler', type=str, default='realesrgan', help='background upsampler. Default: realesrgan')
+    parser.add_argument(
+        '--bg_tile',
+        type=int,
+        default=400,
+        help='Tile size for background sampler, 0 for no tile during testing. Default: 400')
+    parser.add_argument('--suffix', type=str, default=None, help='Suffix of the restored faces')
+    parser.add_argument('--only_center_face', action='store_true', help='Only restore the center face')
+    parser.add_argument('--aligned', action='store_true', help='Input are aligned faces')
+    parser.add_argument(
+        '--ext',
+        type=str,
+        default='auto',
+        help='Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto')
+    parser.add_argument('-w', '--weight', type=float, default=0.5, help='Adjustable weights.')
+    args = parser.parse_args()
+
+    args = parser.parse_args()
+
+    # ------------------------ input & output ------------------------
+    if args.input.endswith('/'):
+        args.input = args.input[:-1]
+    if os.path.isfile(args.input):
+        img_list = [args.input]
+    else:
+        img_list = sorted(glob.glob(os.path.join(args.input, '*')))
+
+    os.makedirs(args.output, exist_ok=True)
+
+    # ------------------------ set up background upsampler ------------------------
+    if args.bg_upsampler == 'realesrgan':
+        if not torch.cuda.is_available() and not torch.has_mps:  # CPU
+            import warnings
+            warnings.warn('The unoptimized RealESRGAN is slow on CPU. We do not use it. '
+                          'If you really want to use it, please modify the corresponding codes.')
+            bg_upsampler = None
+        else:
+            from basicsr.archs.rrdbnet_arch import RRDBNet
+            from realesrgan import RealESRGANer
+            model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
+            bg_upsampler = RealESRGANer(
+                scale=2,
+                model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth',
+                model=model,
+                tile=args.bg_tile,
+                tile_pad=10,
+                pre_pad=0,
+                half=False)  # need to set False in CPU mode
+    else:
+        bg_upsampler = None
+
+    # ------------------------ set up GFPGAN restorer ------------------------
+    if args.version == '1':
+        arch = 'original'
+        channel_multiplier = 1
+        model_name = 'GFPGANv1'
+        url = 'https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/GFPGANv1.pth'
+    elif args.version == '1.2':
+        arch = 'clean'
+        channel_multiplier = 2
+        model_name = 'GFPGANCleanv1-NoCE-C2'
+        url = 'https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth'
+    elif args.version == '1.3':
+        arch = 'clean'
+        channel_multiplier = 2
+        model_name = 'GFPGANv1.3'
+        url = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth'
+    elif args.version == '1.4':
+        arch = 'clean'
+        channel_multiplier = 2
+        model_name = 'GFPGANv1.4'
+        url = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth'
+    elif args.version == 'RestoreFormer':
+        arch = 'RestoreFormer'
+        channel_multiplier = 2
+        model_name = 'RestoreFormer'
+        url = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/RestoreFormer.pth'
+    else:
+        raise ValueError(f'Wrong model version {args.version}.')
+
+    # determine model paths
+    model_path = os.path.join('experiments/pretrained_models', model_name + '.pth')
+    if not os.path.isfile(model_path):
+        model_path = os.path.join('gfpgan/weights', model_name + '.pth')
+    if not os.path.isfile(model_path):
+        # download pre-trained models from url
+        model_path = url
+
+    restorer = GFPGANer(
+        model_path=model_path,
+        upscale=args.upscale,
+        arch=arch,
+        channel_multiplier=channel_multiplier,
+        bg_upsampler=bg_upsampler)
+
+    # ------------------------ restore ------------------------
+    for img_path in img_list:
+        # read image
+        img_name = os.path.basename(img_path)
+        print(f'Processing {img_name} ...')
+        basename, ext = os.path.splitext(img_name)
+        input_img = cv2.imread(img_path, cv2.IMREAD_COLOR)
+
+        # restore faces and background if necessary
+        cropped_faces, restored_faces, restored_img = restorer.enhance(
+            input_img,
+            has_aligned=args.aligned,
+            only_center_face=args.only_center_face,
+            paste_back=True,
+            weight=args.weight)
+
+        # save faces
+        for idx, (cropped_face, restored_face) in enumerate(zip(cropped_faces, restored_faces)):
+            # save cropped face
+            save_crop_path = os.path.join(args.output, 'cropped_faces', f'{basename}_{idx:02d}.png')
+            imwrite(cropped_face, save_crop_path)
+            # save restored face
+            if args.suffix is not None:
+                save_face_name = f'{basename}_{idx:02d}_{args.suffix}.png'
+            else:
+                save_face_name = f'{basename}_{idx:02d}.png'
+            save_restore_path = os.path.join(args.output, 'restored_faces', save_face_name)
+            imwrite(restored_face, save_restore_path)
+            # save comparison image
+            cmp_img = np.concatenate((cropped_face, restored_face), axis=1)
+            imwrite(cmp_img, os.path.join(args.output, 'cmp', f'{basename}_{idx:02d}.png'))
+
+        # save restored img
+        if restored_img is not None:
+            if args.ext == 'auto':
+                extension = ext[1:]
+            else:
+                extension = args.ext
+
+            if args.suffix is not None:
+                save_restore_path = os.path.join(args.output, 'restored_imgs', f'{basename}_{args.suffix}.{extension}')
+            else:
+                save_restore_path = os.path.join(args.output, 'restored_imgs', f'{basename}.{extension}')
+            imwrite(restored_img, save_restore_path)
+
+    print(f'Results are in the [{args.output}] folder.')
+
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,12 @@
+basicsr>=1.4.2
+facexlib>=0.2.5
+lmdb
+numpy
+opencv-python
+pyyaml
+scipy
+tb-nightly
+torch>=1.7
+torchvision
+tqdm
+yapf