Update app.py

app.py

@@ -1,43 +1,20 @@
-from fastapi import FastAPI, HTTPException
-from transformers import pipeline
-from PIL import Image
-import io
-
-app = FastAPI()
-
-# Load the image classification pipeline
-pipe = pipeline("image-classification", model="mateoluksenberg/dit-base-Classifier_CM05")
-
-# Sample image path (for testing)
-image_path = 'cm5.jpg'
-
-# Async function to classify an image
-async def classify_image(image_path: str):
-    try:
-        image = Image.open(image_path).convert('RGB')
-
-        image_bytes = io.BytesIO()
-        image.save(image_bytes, format='JPEG')
-        image_bytes = image_bytes.getvalue()
-
-        # Perform image classification
-        result = pipe(image_bytes)
-
-        return result[0]  # Return the top prediction
-
-    except Exception as e:
-        # Handle exceptions, for example: file not found, image format issues, etc.
-        raise HTTPException(status_code=500, detail=f"Error processing image: {str(e)}")
-
-@app.get("/")
-async def home(image_path: str = image_path):
-    try:
-        result = await classify_image(image_path)
-        return {"message": "Hello World", "classification_result": result}
-
-    except HTTPException as e:
-        raise e
-
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error classifying image: {str(e)}")
-
+
+from transformers import pipeline
+from PIL import Image
+
+# Cargar el pipeline para clasificación de imágenes
+pipe = pipeline("image-classification", model="mateoluksenberg/dit-base-Classifier_CM05")
+
+# Ruta a la imagen que deseas clasificar dentro del contenedor
+image_path = 'cm5.jpg'
+
+# Abrir la imagen desde la ruta local y convertirla a RGB
+image = Image.open(image_path).convert('RGB')
+
+# Realizar la clasificación de la imagen
+result = pipe(image)
+
+# Imprimir el resultado
+print(result)
+
+