Update app.py

app.py

@@ -6,10 +6,6 @@ feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-ima
 tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-
-
-
 model.to(device)
 
 
@@ -24,14 +20,10 @@ def predict_step(image_paths):
     i_image = Image.open(image_path)
     if i_image.mode != "RGB":
       i_image = i_image.convert(mode="RGB")
-
     images.append(i_image)
-
   pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
   pixel_values = pixel_values.to(device)
-
   output_ids = model.generate(pixel_values, **gen_kwargs)
-
   preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
   preds = [pred.strip() for pred in preds]
   return preds
@@ -52,12 +44,16 @@ description= "NLP Image Understanding"
 title = "NLP Image Understanding"
 article = "nlpconnect/vit-gpt2-image-captioning"
 
+input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
+output = gr.outputs.Textbox(type="auto",label="Captions")
+examples = [['35-Favorite-Games.jpg']]
+
 interface = gr.Interface(
         fn=predict,
         inputs = input,
         theme="grass",
         outputs=output,
-        examples = ['35-Favorite-Games.jpg'],
+        examples = examples,
         title=title,
         description=description,
         article = article,