Spaces:
Running
Running
File size: 2,020 Bytes
f23d324 0000b07 f23d324 |
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 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
"""from fastapi import FastAPI
from fastapi.responses import RedirectResponse
import gradio as gr
from transformers import pipeline, ViltProcessor, ViltForQuestionAnswering, AutoTokenizer, AutoModelForCausalLM
from PIL import Image
import torch
import fitz # PyMuPDF for PDF
app = FastAPI()
# ========== Image QA Setup ==========
vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
def answer_question_from_image(image, question):
if image is None or not question.strip():
return "Please upload an image and ask a question."
inputs = vqa_processor(image, question, return_tensors="pt")
with torch.no_grad():
outputs = vqa_model(**inputs)
predicted_id = outputs.logits.argmax(-1).item()
return vqa_model.config.id2label[predicted_id]
# ========== Gradio Interfaces ==========
img_interface = gr.Interface(
fn=answer_question_from_image,
inputs=[gr.Image(label="Upload Image"), gr.Textbox(label="Ask a Question")],
outputs="text",
title="Image Question Answering"
)
# ========== Combine and Mount ==========
demo = gr.TabbedInterface( img_interface , "Image QA")
app = gr.mount_gradio_app(app, demo, path="/")
@app.get("/")
def root():
return RedirectResponse(url="/") """
from transformers import ViltProcessor, ViltForQuestionAnswering
import torch
# Load image QA model once
vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
def answer_question_from_image(image, question):
if image is None or not question.strip():
return "Please upload an image and ask a question."
inputs = vqa_processor(image, question, return_tensors="pt")
with torch.no_grad():
outputs = vqa_model(**inputs)
predicted_id = outputs.logits.argmax(-1).item()
return vqa_model.config.id2label[predicted_id]
|