Update app.py

app.py

@@ -240,12 +240,16 @@ def predict(image):
     # annotated_img = results[0].plot()
     # return annotated_img
 
-    # Preprocess the image (resize, normalize, etc)
+    # Preprocess the image
+
+    # Get name and shape of the model's inputs
     input_name = model.get_inputs()[0].name
     input_shape = model.get_inputs()[0].shape
 
     # Resize the image to the model's input shape
     image = cv2.resize(image, (input_shape[2], input_shape[3]))
+
+    # Reshape the image to match the model's input shape
     image = image.reshape(3, 640, 640)
 
     # Normalize the image
@@ -260,14 +264,17 @@ def predict(image):
     # Convert the image to a numpy array and add a batch dimension
     if len(input_shape) == 4 and input_shape[0] == 1:
         image = np.expand_dims(image, axis=0)
+    image = image.astype(np.float32)
     
-    image = image.astype(np.float32) # after expands/astype (1, 640, 640, 3)
-    
-    # Perform inference
+    # Make prediction
     output = model.run(None, {input_name: image})
+
+    
     print("type output:", type(output))
     print(output)
 
+    # Postprocess output image
+    
     annotated_img = output[0]
     # annotated_img = (output[0] / 255.0 - mean)/std
     # annotated_img = classes[output[0][0].argmax(0)]