Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import torch
+import cv2
+import numpy as np
+from torchvision import transforms
+from PIL import Image
+
+# Load MiDaS depth estimation model
+midas_model = torch.hub.load("intel-isl/MiDaS", "DPT_Hybrid")
+midas_model.eval()
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+midas_model.to(device)
+midas_transform = torch.hub.load("intel-isl/MiDaS", "transforms").default_transform
+
+def estimate_depth(image):
+    """Estimate depth map to identify fabric folds."""
+    image = image.convert("RGB")
+    image_tensor = midas_transform(image).to(device)
+    
+    with torch.no_grad():
+        depth = midas_model(image_tensor).squeeze().cpu().numpy()
+    
+    depth = cv2.resize(depth, (image.size[0], image.size[1]))
+    depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255
+    return depth.astype(np.uint8)
+
+def detect_folds(image):
+    """Apply edge detection and highlight cloth folds."""
+    depth_map = estimate_depth(image)
+    edges = cv2.Canny(depth_map, 50, 150)
+    
+    # Convert edges to 3-channel image for visualization
+    edges_colored = cv2.cvtColor(edges, cv2.COLOR_GRAY2RGB)
+    overlay = cv2.addWeighted(np.array(image), 0.7, edges_colored, 0.3, 0)
+    
+    return Image.fromarray(overlay)
+
+def main(image):
+    return detect_folds(image)
+
+iface = gr.Interface(
+    fn=main,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="Cloth Fold Detection",
+    description="Upload an image of clothing to visualize folds using depth estimation and edge detection."
+)
+
+if __name__ == "__main__":
+    iface.launch(share=True, debug=True)