Update app.py

app.py

@@ -1,38 +1,49 @@
 import fastapi
-from fastapi import FastAPI,UploadFile
+
+from fastapi import FastAPI, UploadFile, File
 from transformers import AutoModelForImageClassification
+
+
 app = FastAPI()
+
+
 # Load the model from the local file
-model = AutoModelForImageClassification.from_pretrained("andupets/real-estate-image-classification-30classes")
+model = AutoModelForImageClassification.from_pretrained(
+    "andupets/real-estate-image-classification-30classes"
+)
+
 
 # Define a function to preprocess the image
-def preprocess_image(image):
-  # Resize the image to a fixed size
-  image = image.resize((224, 224))
+def preprocess_image(image: UploadFile):
+    # Resize the image to a fixed size
+    image = image.resize((224, 224))
 
-  # Convert the image to a NumPy array
-  image = np.array(image)
+    # Convert the image to a NumPy array
+    image = np.array(image)
 
-  # Normalize the image
-  image = image / 255.0
+    # Normalize the image
+    image = image / 255.0
+
+    # Return the image
+    return image
 
-  # Return the image
-  return image
 
 # Define an endpoint to predict the output
 @app.post("/predict")
-async def predict_endpoint(image: UploadFile):
-  # Preprocess the image
-  image = preprocess_image(image)
+async def predict_endpoint(
+    image: UploadFile = File(...)
+):  # Preprocess the image
+    image = preprocess_image(image)
+
+    # Make a prediction
+    prediction = model(image)
 
-  # Make a prediction
-  prediction = model(image)
+    # Return the prediction
+    return {"prediction": prediction}
 
-  # Return the prediction
-  return {"prediction": prediction}
 
 # Start the FastAPI app
 if __name__ == "__main__":
-  import uvicorn
+    import uvicorn
 
-  uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=8000)