Update app.py

app.py

@@ -16,7 +16,7 @@ model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
 def predict(image):
     """Predict the generic image caption from the image """
-    image = image.convert('RGB')
+    # image = image.convert('RGB')
     image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
     clean_text = lambda x: x.replace('<|endoftext|>', '').split('\n')[0]
     caption_ids = model.generate(image, max_length=125)[0]