another changes in names

Dockerfile

@@ -5,10 +5,12 @@ WORKDIR /code
 # Install system dependencies
 RUN apt-get update && apt-get install -y libgl1 libglib2.0-0
 
+# Copy dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Copy app code
 COPY . .
 
-# Run FastAPI with Uvicorn on HF's expected port
+# Run FastAPI with Uvicorn on the correct file and port
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,5 +1,5 @@
 ---
-title: YOLO FastAPI App
+title: YOLO FastAPI Deploy
 emoji: 🤖
 colorFrom: blue
 colorTo: green
@@ -8,6 +8,7 @@ app_file: main.py
 pinned: false
 ---
 
-# YOLO Object Detection API 🚀
+# YOLO FastAPI Deployment 🚀
 
-This runs a FastAPI app serving a pretrained YOLOv8 model.
+This Space deploys a YOLO model with FastAPI.  
+Use `/docs` to test endpoints, or send requests from Postman.

main.py

@@ -1,46 +1,32 @@
-from fastapi import FastAPI, File, UploadFile
+from fastapi import FastAPI, UploadFile, File
 from ultralytics import YOLO
-import uvicorn
-import cv2
-import numpy as np
-from io import BytesIO
-from PIL import Image
-import base64
-
-# Load pretrained YOLOv11 model
-model = YOLO("yolo11s.pt")
+import shutil
+import uuid
+import os
 
+# Initialize FastAPI
 app = FastAPI()
 
+# Load YOLO model (small version for speed)
+model = YOLO("yolo11s.pt")  # or yolov8n.pt if you prefer
+
+UPLOAD_DIR = "uploads"
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+
+
 @app.post("/detect")
 async def detect(file: UploadFile = File(...)):
-    # Read image from user
-    contents = await file.read()
-    image = Image.open(BytesIO(contents)).convert("RGB")
-
-    # Run YOLO inference
-    results = model.predict(image)
-
-    # Extract detections
-    detections = []
-    for r in results:
-        for box in r.boxes:
-            cls = int(box.cls[0].item())
-            conf = float(box.conf[0].item())
-            detections.append({
-                "class": model.names[cls],
-                "confidence": conf
-            })
-
-    # Optionally return annotated image
-    annotated_frame = results[0].plot()  # numpy array (BGR)
-    _, buffer = cv2.imencode(".jpg", annotated_frame)
-    img_base64 = base64.b64encode(buffer).decode("utf-8")
-
-    return {
-        "detections": detections,
-        "annotated_image": f"data:image/jpeg;base64,{img_base64}"
-    }
-
-# if __name__ == "__main__":
-#     uvicorn.run(app, host="0.0.0.0", port=8000)
+    # Save the uploaded file
+    file_id = str(uuid.uuid4())
+    file_path = os.path.join(UPLOAD_DIR, f"{file_id}_{file.filename}")
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
+    # Run YOLO detection
+    results = model(file_path)
+
+    # Save result image
+    result_path = f"{file_path}_result.jpg"
+    results[0].save(filename=result_path)
+
+    return {"message": "Detection complete", "result_file": result_path}

requirements.txt

@@ -1,6 +1,6 @@
-ultralytics
 fastapi
 uvicorn
+ultralytics
 python-multipart
 pillow
-opencv-python-headless
+opencv-python-headless