Update app.py

app.py

@@ -10,6 +10,7 @@ extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-capti
 tokeniser = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 def generate_captions(image):
+    image = Image.open(image).convert("RGB")
     generated_caption = tokeniser.decode(model.generate(extractor(image, return_tensors="pt").pixel_values.to("cpu"))[0])
     sentence = generated_caption
     text_to_remove = "<|endoftext|>"
@@ -48,7 +49,7 @@ def main():
         image = Image.open(uploaded_file).convert("RGB")
         
         # context as prompt
-        prompt = generate_captions(image)
+        prompt = generate_captions(uploaded_file)
         st.write("The Context is:", prompt)
 
         # display the image