Add Zero GPU Gradio app for anime face detection

README.md

@@ -1,13 +1,46 @@
 ---
-title: Anime Face Detector Gpu
-emoji: 👁
-colorFrom: yellow
-colorTo: gray
+title: Anime Face Detector GPU
+emoji: "\U0001F3AD"
+colorFrom: blue
+colorTo: purple
 sdk: gradio
-sdk_version: 6.0.1
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Anime Face Detector (GPU)
+
+Detect anime faces and 28 facial landmarks using YOLOv3 + HRNetV2.
+
+This Space uses **Zero GPU** for fast inference without constant GPU allocation costs.
+
+## Features
+
+- Face detection using YOLOv3
+- 28 facial landmark detection using HRNetV2
+- Adjustable confidence thresholds
+
+## Usage
+
+1. Upload an anime image
+2. Adjust the face and landmark score thresholds
+3. Click Submit to detect faces
+
+## Links
+
+- [Original Repository (hysts)](https://github.com/hysts/anime-face-detector)
+- [Fork with GPU Docker (ayutaz)](https://github.com/ayutaz/anime-face-detector)
+- [Docker Image (ghcr.io)](https://ghcr.io/ayutaz/anime-face-detector)
+
+## Citation
+
+```bibtex
+@misc{anime-face-detector,
+  author = {hysts},
+  title = {Anime Face Detector},
+  year = {2021},
+  howpublished = {\url{https://github.com/hysts/anime-face-detector}}
+}
+```

app.py

@@ -0,0 +1,111 @@
+"""Anime Face Detector - Hugging Face Space with Zero GPU support"""
+import os
+import subprocess
+import sys
+
+# Install mmcv, mmdet, mmpose using mim before importing
+def install_mmlab():
+    subprocess.run([sys.executable, '-m', 'pip', 'install', 'openmim'], check=True)
+    subprocess.run([sys.executable, '-m', 'mim', 'install', 'mmengine', 'mmcv', 'mmdet', 'mmpose'], check=True)
+
+# Check if mmcv is installed
+try:
+    import mmcv
+except ImportError:
+    print('Installing OpenMMLab dependencies...')
+    install_mmlab()
+
+import spaces
+import gradio as gr
+import cv2
+import numpy as np
+import PIL.Image
+import torch
+
+# Global detector (initialized on first GPU call)
+detector = None
+
+
+@spaces.GPU
+def detect(image: np.ndarray, face_score_threshold: float, landmark_score_threshold: float) -> PIL.Image.Image:
+    """Detect anime faces and landmarks in the image."""
+    global detector
+
+    # Lazy initialization on GPU
+    if detector is None:
+        from anime_face_detector import create_detector
+        detector = create_detector('yolov3', device='cuda:0')
+
+    # Convert RGB to BGR for OpenCV
+    image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+
+    # Run detection
+    preds = detector(image_bgr)
+
+    # Draw results
+    res = image_bgr.copy()
+    for pred in preds:
+        box = pred['bbox']
+        box, score = box[:4], box[4]
+        if score < face_score_threshold:
+            continue
+        box = np.round(box).astype(int)
+
+        # Line thickness based on face size
+        lt = max(2, int(3 * (box[2:] - box[:2]).max() / 256))
+
+        # Draw bounding box
+        cv2.rectangle(res, tuple(box[:2]), tuple(box[2:]), (0, 255, 0), lt)
+
+        # Draw confidence score
+        cv2.putText(res, f'{score * 100:.1f}%', (box[0], box[1] - 5),
+                    cv2.FONT_HERSHEY_SIMPLEX, lt / 3, (255, 255, 255), thickness=max(lt // 2, 1))
+
+        # Draw keypoints
+        pred_pts = pred['keypoints']
+        for *pt, kpt_score in pred_pts:
+            if kpt_score < landmark_score_threshold:
+                color = (0, 255, 255)  # Yellow for low confidence
+            else:
+                color = (0, 0, 255)  # Red for high confidence
+            pt = tuple(np.round(pt).astype(int))
+            cv2.circle(res, pt, lt, color, cv2.FILLED)
+
+    # Convert BGR to RGB for output
+    res = cv2.cvtColor(res, cv2.COLOR_BGR2RGB)
+    return PIL.Image.fromarray(res)
+
+
+# Download sample image
+def download_sample():
+    sample_path = 'input.jpg'
+    if not os.path.exists(sample_path):
+        torch.hub.download_url_to_file(
+            'https://raw.githubusercontent.com/hysts/anime-face-detector/main/assets/input.jpg',
+            sample_path
+        )
+    return sample_path
+
+
+# Create Gradio interface
+sample_path = download_sample()
+
+demo = gr.Interface(
+    fn=detect,
+    inputs=[
+        gr.Image(type='numpy', label='Input Image'),
+        gr.Slider(0, 1, step=0.05, value=0.5, label='Face Score Threshold'),
+        gr.Slider(0, 1, step=0.05, value=0.3, label='Landmark Score Threshold'),
+    ],
+    outputs=gr.Image(type='pil', label='Output'),
+    title='Anime Face Detector (GPU)',
+    description='Detect anime faces and 28 facial landmarks using YOLOv3 + HRNetV2. Powered by Zero GPU.',
+    article='<a href="https://github.com/hysts/anime-face-detector">GitHub</a> | <a href="https://github.com/ayutaz/anime-face-detector">Fork with GPU Docker</a>',
+    examples=[
+        [sample_path, 0.5, 0.3],
+    ],
+    cache_examples=False,
+)
+
+if __name__ == '__main__':
+    demo.launch()

packages.txt

@@ -0,0 +1,2 @@
+libgl1
+libglib2.0-0

requirements.txt

@@ -0,0 +1,7 @@
+torch
+torchvision
+openmim
+anime-face-detector
+opencv-python-headless
+gradio>=4.0.0
+spaces