Update app.py

app.py

@@ -3,7 +3,6 @@ from transformers import ViltProcessor, ViltForQuestionAnswering
 import torch
 
 torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
-torch.hub.download_url_to_file('https://computing.ece.vt.edu/~harsh/visualAttention/ProjectWebpage/Figures/vqa_1.png', 'banana.png')
 
 processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
@@ -24,7 +23,7 @@ def answer_question(image, text):
 image = gr.inputs.Image(type="pil")
 question = gr.inputs.Textbox(label="Question")
 answer = gr.outputs.Textbox(label="Predicted answer")
-examples = [["cats.jpg", "How many cats are there?"], ["banana.png", "What is the mustache made of?"]]
+examples = [["cats.jpg", "How many cats are there?"]]
 
 title = "Interactive demo: ViLT"
 description = "Gradio Demo for ViLT (Vision and Language Transformer), fine-tuned on VQAv2. To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."