Fix

app.py

@@ -1,10 +1,8 @@
-# app.py
 from fastapi import FastAPI, File, UploadFile, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
+from inference import ObjectDetector
 import numpy as np
 import cv2
-from inference import ObjectDetector
-from typing import List
 
 # Configuration
 MODEL_ONNX_PATH = "model.onnx"
@@ -30,22 +28,38 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-@app.post("/detect", response_model=List[dict])
+@app.get("/")
+def health_check():
+    return {"status": "OK", "model": "Object Detection API"}
+
+@app.post("/detect")
 async def detect_objects(file: UploadFile = File(...)):
     try:
+        # Validate input
         if not file.content_type.startswith("image/"):
-            raise HTTPException(400, "Invalid file type")
+            raise HTTPException(400, "File must be an image")
 
+        # Read and decode image
         image_data = await file.read()
         image = cv2.imdecode(np.frombuffer(image_data, np.uint8), cv2.IMREAD_COLOR)
-        
         if image is None:
             raise HTTPException(400, "Invalid image data")
 
+        # Perform detection
         detections = detector.predict(image)
-        return detections
+        
+        return {
+            "status": "success",
+            "detections": detections,
+            "count": len(detections)
+        }
 
-    except HTTPException as he:
-        raise he
+    except HTTPException:
+        raise
     except Exception as e:
-        return {"error": str(e)}
+        raise HTTPException(500, f"Processing error: {str(e)}")
+
+# For Hugging Face Spaces
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

inference.py

@@ -1,4 +1,3 @@
-# inference.py
 import numpy as np
 import cv2
 import onnxruntime as ort
@@ -34,6 +33,7 @@ class ObjectDetector:
         intersection_area = np.maximum(0, xmax - xmin) * np.maximum(0, ymax - ymin)
         box_area = (box[2] - box[0]) * (box[3] - box[1])
         boxes_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
+        
         return intersection_area / (box_area + boxes_area - intersection_area + 1e-6)
 
     @staticmethod
@@ -107,6 +107,7 @@ class ObjectDetector:
         } for i in indices]
 
     def predict(self, image: np.ndarray) -> List[Dict]:
+        """Main prediction method"""
         input_tensor, scale, padding = self.preprocess(image)
         outputs = self.session.run(None, {"images": input_tensor})
         return self.postprocess(outputs[0], image.shape[:2], scale, padding)

requirements.txt

@@ -5,4 +5,5 @@ onnxruntime-gpu
 opencv-python
 Pillow
 torch
-ultralytics
+ultralytics
+python-multipart