Add files

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "bizarre-pose-estimator"]
+	path = bizarre-pose-estimator
+	url = https://github.com/ShuhongChen/bizarre-pose-estimator

app.py

@@ -0,0 +1,161 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import argparse
+import functools
+import os
+import pathlib
+import subprocess
+import sys
+
+# workaround for https://github.com/gradio-app/gradio/issues/483
+command = 'pip install -U gradio==2.7.0'
+subprocess.call(command.split())
+
+import gradio as gr
+import huggingface_hub
+import PIL.Image
+import torch
+import torchvision
+
+sys.path.insert(0, 'bizarre-pose-estimator')
+
+from _util.twodee_v0 import I as ImageWrapper
+
+TOKEN = os.environ['TOKEN']
+
+MODEL_REPO = 'hysts/bizarre-pose-estimator-models'
+MODEL_PATH = 'tagger.pth'
+LABEL_PATH = 'tags.txt'
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--device', type=str, default='cpu')
+    parser.add_argument('--score-slider-step', type=float, default=0.05)
+    parser.add_argument('--score-threshold', type=float, default=0.5)
+    parser.add_argument('--theme', type=str, default='dark-grass')
+    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()
+
+
+def download_sample_images() -> list[pathlib.Path]:
+    image_dir = pathlib.Path('samples')
+    image_dir.mkdir(exist_ok=True)
+
+    dataset_repo = 'hysts/sample-images-TADNE'
+    n_images = 36
+    paths = []
+    for index in range(n_images):
+        path = huggingface_hub.hf_hub_download(dataset_repo,
+                                               f'{index:02d}.jpg',
+                                               repo_type='dataset',
+                                               cache_dir=image_dir.as_posix(),
+                                               use_auth_token=TOKEN)
+        paths.append(pathlib.Path(path))
+    return paths
+
+
+@torch.inference_mode()
+def predict(image: PIL.Image.Image, score_threshold: float,
+            device: torch.device, model: torch.nn.Module,
+            labels: list[str]) -> dict[str, float]:
+    data = ImageWrapper(image).resize_square(256).alpha_bg(
+        c='w').convert('RGB').tensor()
+    data = data.to(device).unsqueeze(0)
+
+    preds = model(data)[0]
+    preds = torch.sigmoid(preds)
+    preds = preds.cpu().numpy().astype(float)
+
+    res = dict()
+    for prob, label in zip(preds, labels):
+        if prob < score_threshold:
+            continue
+        res[label] = prob
+    return res
+
+
+def load_model(device: torch.device) -> torch.nn.Module:
+    model_path = huggingface_hub.hf_hub_download(MODEL_REPO,
+                                                 MODEL_PATH,
+                                                 use_auth_token=TOKEN)
+    state_dict = torch.load(model_path)
+
+    model = torchvision.models.resnet50(num_classes=1062)
+    model.load_state_dict(state_dict)
+    model.to(device)
+    model.eval()
+
+    return model
+
+
+def load_labels() -> list[str]:
+    label_path = huggingface_hub.hf_hub_download(MODEL_REPO,
+                                                 LABEL_PATH,
+                                                 use_auth_token=TOKEN)
+    with open(label_path) as f:
+        labels = [line.strip() for line in f.readlines()]
+    return labels
+
+
+def main():
+    gr.close_all()
+
+    args = parse_args()
+    device = torch.device(args.device)
+
+    image_paths = download_sample_images()
+    examples = [[path.as_posix(), args.score_threshold]
+                for path in image_paths]
+
+    model = load_model(device)
+    labels = load_labels()
+
+    func = functools.partial(predict,
+                             device=device,
+                             model=model,
+                             labels=labels)
+    func = functools.update_wrapper(func, predict)
+
+    repo_url = 'https://github.com/ShuhongChen/bizarre-pose-estimator'
+    title = 'ShuhongChen/bizarre-pose-estimator (tagger)'
+    description = f'A demo for {repo_url}'
+    article = None
+
+    gr.Interface(
+        func,
+        [
+            gr.inputs.Image(type='pil', label='Input'),
+            gr.inputs.Slider(0,
+                             1,
+                             step=args.score_slider_step,
+                             default=args.score_threshold,
+                             label='Score Threshold'),
+        ],
+        gr.outputs.Label(label='Output'),
+        theme=args.theme,
+        title=title,
+        description=description,
+        article=article,
+        examples=examples,
+        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()

bizarre-pose-estimator

@@ -0,0 +1 @@
+Subproject commit 7382ec234fa40cd8a6ec4a28b4639209199bc035

requirements.txt

@@ -0,0 +1,2 @@
+torch>=1.10.1
+torchvision>=0.11.2