File size: 2,028 Bytes
bc7d231
 
c7c92f9
 
dfda773
58e3cb5
bc7d231
d5a60de
bc7d231
 
9d0134c
dc81fd5
 
 
 
 
 
 
 
 
bc7d231
 
 
 
 
 
 
 
 
58e3cb5
 
bc7d231
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
53
54
55
56
57
import streamlit as st
import torch
import bitsandbytes
import accelerate
import scipy
from PIL import Image

from transformers import Blip2Processor, Blip2ForConditionalGeneration, InstructBlipProcessor, InstructBlipForConditionalGeneration


def load_caption_model(blip2=False, instructblip=True):

    if blip2:
        processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
        model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", load_in_8bit=True,torch_dtype=torch.float16, device_map="auto")
        #model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16, device_map="auto")
        
    if instructblip:
        model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b", load_in_8bit=True,torch_dtype=torch.float16, device_map="auto")
        processor = InstructBlipProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b")

    return model, processor

    

def answer_question(image, question, model, processor):
    
    
    image = Image.open(image).convert('RGB')
    


    inputs = processor(image, question, return_tensors="pt").to("cuda", torch.float16)

    out = model.generate(**inputs, max_length=200, min_length=20, num_beams=1)

    answer = processor.decode(out[0], skip_special_tokens=True).strip()
    return answer

st.title("Image Question Answering")

# File uploader for the image
image = st.file_uploader("Upload an image", type=["png", "jpg", "jpeg"])

# Text input for the question
question = st.text_input("Enter your question about the image:")

if st.button("Get Answer"):
    if image is not None and question:
        # Display the image
        st.image(image, use_column_width=True)
        # Get and display the answer
        model, processor = load_caption_model()
        answer = answer_question(image, question, model, processor)
        st.write(answer)
    else:
        st.write("Please upload an image and enter a question.")