app.py

import streamlit as st
import torch
import bitsandbytes
import accelerate
import scipy
from PIL import Image
import torch.nn as nn
from transformers import Blip2Processor, Blip2ForConditionalGeneration, InstructBlipProcessor, InstructBlipForConditionalGeneration
from my_model.object_detection import detect_and_draw_objects

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

    if blip2:
        processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b", load_in_8bit=True,torch_dtype=torch.float16)
        model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", load_in_8bit=True,torch_dtype=torch.float16)
        if torch.cuda.device_count() > 1:
            model = nn.DataParallel(model)
            model.to('cuda')
        #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)
        if torch.cuda.device_count() > 1:
            model = nn.DataParallel(model)
            model.to('cuda')
        processor = InstructBlipProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b", load_in_8bit=True,torch_dtype=torch.float16)

    return model, processor

    

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

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

    if isinstance(model, torch.nn.DataParallel):
    # Use the 'module' attribute to access the original model
        out = model.module.generate(**inputs, max_length=100, min_length=20)
    else:
       
        out = model.generate(**inputs, max_length=100, min_length=20)

    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.")






# Object Detection

# Object Detection UI in the sidebar
st.sidebar.title("Object Detection")
# Dropdown to select the model
detect_model = st.sidebar.selectbox("Choose a model for object detection:", ["detic", "yolov5"])
# Slider for threshold with default values based on the model
threshold = st.sidebar.slider("Select Detection Threshold", 0.1, 0.9, 0.2 if detect_model == "yolov5" else 0.4)
# Button to trigger object detection
detect_button = st.sidebar.button("Detect Objects")


def perform_object_detection(image, model_name, threshold):
    """
    Perform object detection on the given image using the specified model and threshold.

    Args:
    image (PIL.Image): The image on which to perform object detection.
    model_name (str): The name of the object detection model to use.
    threshold (float): The threshold for object detection.

    Returns:
    PIL.Image, str: The image with drawn bounding boxes and a string of detected objects.
    """


    
    # Perform object detection and draw bounding boxes
    st.write("9999999999999")
    processed_image, detected_objects = detect_and_draw_objects(image, model_name, threshold)
    st.write("66666666666666")
    st.write(detected_objects[:20])
    return processed_image, detected_objects



# Check if the 'Detect Objects' button was clicked
if detect_button:
    if image is not None:
        # Open the uploaded image
        try:
            image = Image.open(image)
            st.write("1111111111111")
            # Display the original image
            st.image(image, use_column_width=True, caption="Original Image")
            st.write("22222222222222")
            # Perform object detection
            processed_image, detected_objects = perform_object_detection(image, detect_model, threshold)
            st.write(detected_objects)
            st.write("333333333333333")
            st.write(processed_image)
            st.write(type(processed_image))
            #if processed_image:
            # Display the image with detected objects
            st.image(processed_image, use_column_width=True, caption="Image with Detected Objects")
            st.write("444444444444444")
            # Display the detected objects as text
            st.write(detected_objects)
            st.write("5555555555555555")
            #else:
            #    st.error("Failed to process image for object detection.")

        except Exception as e:
            st.error(f"Error loading image: {e}")

    else:
        st.write("Please upload an image for object detection.")