Update app.py

app.py

@@ -4,7 +4,6 @@ from transformers import  ViTImageProcessor, VisionEncoderDecoderModel,RobertaTo
 import PIL 
 import streamlit as st
 from PIL import Image
-import trasformer
 
 
 def set_page_config():
@@ -33,13 +32,9 @@ def image_preprocess(image):
 
 def generate_caption(image_processor, model, tokenizer,device, image):
     inputs = image_processor(image, return_tensors='pt')
-    print(inputs)
-    model.eval()
-    # Generate caption
-    with torch.no_grad():
-      output = model.generate(pixel_values=inputs)
-      # Decode the generated caption
-      caption = tokenizer.decode(output[0], skip_special_tokens=True)
+    output = model.generate(**inputs)
+
+    caption = tokenizer.decode(output[0], skip_special_tokens=True)
     return caption