Update app.py

app.py

@@ -18,9 +18,7 @@ def predict(image,max_length=64, num_beams=4):
   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(sample, max_length = max_length)[0]
-  print("*"*20)
-  print(caption_ids)
+  caption_ids = model.generate(image, max_length = max_length)[0]
   caption_text = clean_text(tokenizer.decode(caption_ids))
   return caption_text 
 
@@ -32,12 +30,14 @@ output = gr.outputs.Textbox(type="auto",label="Captions")
 
 article = "This HuggingFace Space presents a demo for Image captioning in Hindi built with VIT Encoder and GPT2 Decoder"
 title = "Hindi Image Captioning System"
+examples = [f"./example_{i}.jpg" for i in range(1,5)]
+
 interface = gr.Interface(
         fn=predict,
         inputs = input,
         theme="grass",
         outputs=output,
- #       examples = examples,
+        examples = examples,
         title=title,
         description=article,
     )