Update app.py

app.py

@@ -39,6 +39,7 @@ import torch
 #     f1_metric.set(f1)
 
 feature_extractor = ViTImageProcessor.from_pretrained("model")
+print(feature_extractor)
 cap_model = VisionEncoderDecoderModel.from_pretrained("model")
 tokenizer = AutoTokenizer.from_pretrained("model")
 
@@ -61,7 +62,7 @@ def generate_caption(processor, model, image, tokenizer=None):
   # return preds
     inputs = processor(images=image, return_tensors="pt").to(device)
     
-    generated_ids = model.generate(pixel_values=inputs.pixel_values, max_length=50)
+    generated_ids = model.generate(pixel_values=inputs.pixel_values)
 
     if tokenizer is not None:
         generated_caption = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]