Update app.py

app.py

@@ -4,11 +4,13 @@ import torch
 from PIL import Image, ImageDraw
 import io
 import base64
-from fastapi import FastAPI, File, UploadFile
+from fastapi import FastAPI, File, UploadFile, Form
 from fastapi.middleware.cors import CORSMiddleware
 import numpy as np
 import json
 from starlette.responses import JSONResponse
+import uvicorn
+from threading import Thread
 
 # FastAPI app
 app = FastAPI()
@@ -53,17 +55,13 @@ def draw_boxes(image, predictions, threshold=0.6):
     return image, filtered_preds
 
 # API Endpoint
-@app.post("/detect")
-async def detect_fracture(file: UploadFile = File(...), confidence: float = 0.6):
+@app.post("/api/predict")
+async def predict(file: UploadFile = File(...), confidence: float = Form(default=0.6)):
     try:
-        # Read and process image
         contents = await file.read()
         image = Image.open(io.BytesIO(contents))
         
-        # Get predictions from all models
-        results = {}
-        
-        # Object detection models
+        # Object detection
         detection_preds = models["D3STRON"](image)
         result_image = image.copy()
         result_image, filtered_detections = draw_boxes(result_image, detection_preds, confidence)
@@ -74,7 +72,7 @@ async def detect_fracture(file: UploadFile = File(...), confidence: float = 0.6)
         img_byte_arr = img_byte_arr.getvalue()
         img_b64 = base64.b64encode(img_byte_arr).decode()
         
-        # Classification models
+        # Classifications
         class_results = {
             "Heem2": models["Heem2"](image),
             "Nandodeomkar": models["Nandodeomkar"](image)
@@ -91,19 +89,51 @@ async def detect_fracture(file: UploadFile = File(...), confidence: float = 0.6)
         return JSONResponse({
             "success": False,
             "error": str(e)
-        })
+        }, status_code=500)
 
 # Streamlit UI
 def main():
     st.title("🦴 Fraktur Detektion")
     
-    # UI elements...
     uploaded_file = st.file_uploader("Röntgenbild hochladen", type=['png', 'jpg', 'jpeg'])
     confidence = st.slider("Konfidenzschwelle", 0.0, 1.0, 0.6, 0.05)
     
     if uploaded_file:
-        # Process image and display results...
-        pass
+        # Afficher l'image originale
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Original Röntgenbild", use_column_width=True)
+        
+        if st.button("Analysieren"):
+            with st.spinner('Analyse läuft...'):
+                # Object detection
+                detection_preds = models["D3STRON"](image)
+                result_image = image.copy()
+                result_image, filtered_detections = draw_boxes(result_image, detection_preds, confidence)
+                
+                # Afficher l'image avec les détections
+                st.image(result_image, caption="Erkannte Frakturen", use_column_width=True)
+                
+                # Afficher les détections
+                st.subheader("Detektionen:")
+                for detection in filtered_detections:
+                    st.write(f"- {detection['label']}: {detection['score']:.2%}")
+                
+                # Classifications
+                st.subheader("Klassifikationen:")
+                class_results = {
+                    "Heem2": models["Heem2"](image),
+                    "Nandodeomkar": models["Nandodeomkar"](image)
+                }
+                st.json(class_results)
+
+def run_fastapi():
+    uvicorn.run(app, host="0.0.0.0", port=8000)
 
 if __name__ == "__main__":
+    # Démarrer FastAPI dans un thread séparé
+    api_thread = Thread(target=run_fastapi)
+    api_thread.daemon = True
+    api_thread.start()
+    
+    # Lancer Streamlit
     main()