File size: 1,234 Bytes
e2e136b 3f05b71 c09b2b3 e2e136b 3f05b71 e2e136b 3f05b71 e2e136b c09b2b3 1a8bb86 e2e136b 1fdcfa0 e2e136b 6b4fe24 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
import gradio as gr
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://cdn.openai.com/dall-e-2/demos/text2im/astronaut/horse/photo/0.jpg', 'astronaut.jpg')
def getAnswer(query, image):
encoding = processor(image, text, return_tensors="pt")
# forward pass
with torch.no_grad():
outputs = model(**encoding)
logits = outputs.logits
idx = logits.argmax(-1).item()
predicted_answer = model.config.id2label[idx]
return predicted_answer
image = gr.inputs.Image(type="pil")
question = gr.inputs.Textbox(label="Question about the image")
answer = gr.outputs.Textbox(label="Predicted answer")
examples = [["cats.jpg", "How many cats are there?"], ["astronaut.jpg", "What's the astronaut riding on?"]]
title="Visual question and answering"
iface = gr.Interface(fn=getAnswer,
inputs=[image, question],
outputs=answer,
examples=examples,
title=title,
enable_queue=True)
iface.launch(debug=True )
|