Add files

.gitattributes

@@ -1,3 +1,4 @@
+*.jpg filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "CelebAMask-HQ"]
+	path = CelebAMask-HQ
+	url = https://github.com/switchablenorms/CelebAMask-HQ

CelebAMask-HQ

@@ -0,0 +1 @@
+Subproject commit 3f6c45df5e67130568f9459f24f8d6a5ff836d30

app.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import argparse
+import functools
+import os
+import pathlib
+import sys
+from typing import Callable
+
+import gradio as gr
+import numpy as np
+import PIL.Image
+import torch
+import torch.nn as nn
+import torchvision.transforms as T
+from huggingface_hub import hf_hub_download
+
+sys.path.insert(0, 'CelebAMask-HQ/face_parsing')
+
+from unet import unet
+from utils import generate_label
+
+ORIGINAL_REPO_URL = 'https://github.com/switchablenorms/CelebAMask-HQ'
+TITLE = 'CelebAMask-HQ Face Parsing'
+DESCRIPTION = f'This is a demo for the model provided in {ORIGINAL_REPO_URL}.'
+ARTICLE = None
+
+TOKEN = os.environ['TOKEN']
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--device', type=str, default='cpu')
+    parser.add_argument('--theme', type=str)
+    parser.add_argument('--live', action='store_true')
+    parser.add_argument('--share', action='store_true')
+    parser.add_argument('--port', type=int)
+    parser.add_argument('--disable-queue',
+                        dest='enable_queue',
+                        action='store_false')
+    parser.add_argument('--allow-flagging', type=str, default='never')
+    parser.add_argument('--allow-screenshot', action='store_true')
+    return parser.parse_args()
+
+
+@torch.inference_mode()
+def predict(image: PIL.Image.Image, model: nn.Module, transform: Callable,
+            device: torch.device) -> np.ndarray:
+    data = transform(image)
+    data = data.unsqueeze(0).to(device)
+    out = model(data)
+    out = generate_label(out, 512)
+    out = out[0].cpu().numpy().transpose(1, 2, 0)
+    out = np.clip(np.round(out * 255), 0, 255).astype(np.uint8)
+
+    res = np.asarray(image.resize(
+        (512, 512))).astype(float) * 0.5 + out.astype(float) * 0.5
+    res = np.clip(np.round(res), 0, 255).astype(np.uint8)
+    return out, res
+
+
+def load_model(device: torch.device) -> nn.Module:
+    path = hf_hub_download('hysts/CelebAMask-HQ-Face-Parsing',
+                           'models/model.pth',
+                           use_auth_token=TOKEN)
+    state_dict = torch.load(path, map_location='cpu')
+    model = unet()
+    model.load_state_dict(state_dict)
+    model.eval()
+    model.to(device)
+    return model
+
+
+def main():
+    gr.close_all()
+
+    args = parse_args()
+    device = torch.device(args.device)
+
+    model = load_model(device)
+    transform = T.Compose([
+        T.Resize((512, 512), interpolation=PIL.Image.NEAREST),
+        T.ToTensor(),
+        T.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
+    ])
+
+    func = functools.partial(predict,
+                             model=model,
+                             transform=transform,
+                             device=device)
+    func = functools.update_wrapper(func, predict)
+
+    image_dir = pathlib.Path('images')
+    examples = [[path.as_posix()] for path in sorted(image_dir.glob('*.jpg'))]
+
+    gr.Interface(
+        func,
+        gr.inputs.Image(type='pil', label='Input'),
+        [
+            gr.outputs.Image(type='numpy', label='Predicted Labels'),
+            gr.outputs.Image(type='numpy', label='Masked'),
+        ],
+        examples=examples,
+        title=TITLE,
+        description=DESCRIPTION,
+        article=ARTICLE,
+        theme=args.theme,
+        allow_screenshot=args.allow_screenshot,
+        allow_flagging=args.allow_flagging,
+        live=args.live,
+    ).launch(
+        enable_queue=args.enable_queue,
+        server_port=args.port,
+        share=args.share,
+    )
+
+
+if __name__ == '__main__':
+    main()

images/README.md

@@ -0,0 +1,7 @@
+These images are freely-usable ones from [Unsplash](https://unsplash.com/).
+
+- https://unsplash.com/photos/rDEOVtE7vOs
+- https://unsplash.com/photos/et_78QkMMQs
+- https://unsplash.com/photos/ILip77SbmOE
+- https://unsplash.com/photos/95UF6LXe-Lo
+

requirements.txt

@@ -0,0 +1,5 @@
+numpy==1.22.3
+opencv-python-headless==4.5.5.62
+Pillow==9.0.1
+torch==1.11.0
+torchvision==0.12.0