File size: 4,897 Bytes
bc7d231 c7c92f9 dfda773 58e3cb5 63fc765 d5a60de 5554139 e9d7d81 fdc69a0 bc7d231 1d94d91 f35e4aa 1d94d91 f35e4aa 1d94d91 f35e4aa 3ec7dfb 1d94d91 f950e4a 1d94d91 3ec7dfb f35e4aa 3ec7dfb f35e4aa 3ec7dfb 1d94d91 f35e4aa |
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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
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
from my_model.captioner.image_captioning import get_caption
from my_model.utilities import free_gpu_resources
# Placeholder for undefined functions
def load_caption_model():
st.write("Placeholder for load_caption_model function")
return None, None
def answer_question(image, question, model, processor):
return "Placeholder answer for the question"
def detect_and_draw_objects(image, model_name, threshold):
return image, "Detected objects"
def get_caption(image):
return "Generated caption for the image"
def free_gpu_resources():
pass
# Main function
def main():
st.sidebar.title("Navigation")
selection = st.sidebar.radio("Go to", ["Home", "Dataset Analysis", "Evaluation Results", "Run Inference", "Dissertation Report", "Object Detection"])
if selection == "Home":
display_home()
elif selection == "Dissertation Report":
display_dissertation_report()
elif selection == "Evaluation Results":
display_evaluation_results()
elif selection == "Dataset Analysis":
display_dataset_analysis()
elif selection == "Run Inference":
run_inference()
elif selection == "Object Detection":
run_object_detection()
def display_home():
st.title("MultiModal Learning for Knowledge-Based Visual Question Answering")
st.write("Home page content goes here...")
def display_dissertation_report():
st.title("Dissertation Report")
st.write("Click the link below to view the PDF.")
st.download_button(
label="Download PDF",
data=open("Files/Dissertation Report.pdf", "rb"),
file_name="example.pdf",
mime="application/octet-stream"
)
def display_evaluation_results():
st.title("Evaluation Results")
st.write("This is a Place Holder until the contents are uploaded.")
def display_dataset_analysis():
st.title("OK-VQA Dataset Analysis")
st.write("This is a Place Holder until the contents are uploaded.")
def run_inference():
st.title("Image-based Q&A App")
# Image-based Q&A functionality
image_qa_app()
def run_object_detection():
st.title("Object Detection")
# Object Detection functionality
# ... Implement your code for this section ...
def image_qa_app():
# Initialize session state for storing images and their Q&A histories
if 'images_qa_history' not in st.session_state:
st.session_state['images_qa_history'] = []
# Button to clear all data
if st.button('Clear All'):
st.session_state['images_qa_history'] = []
st.experimental_rerun()
# Image uploader
uploaded_image = st.file_uploader("Upload an Image", type=["png", "jpg", "jpeg"])
if uploaded_image is not None:
image = Image.open(uploaded_image)
current_image_key = uploaded_image.name # Use image name as a unique key
# Check if the image is already in the history
if not any(info['image_key'] == current_image_key for info in st.session_state['images_qa_history']):
st.session_state['images_qa_history'].append({
'image_key': current_image_key,
'image': image,
'qa_history': []
})
# Display all images and their Q&A histories
for image_info in st.session_state['images_qa_history']:
st.image(image_info['image'], caption='Uploaded Image.', use_column_width=True)
for q, a in image_info['qa_history']:
st.text(f"Q: {q}\nA: {a}\n")
# If the current image is being processed
if image_info['image_key'] == current_image_key:
# Unique keys for each widget
question_key = f"question_{current_image_key}"
button_key = f"button_{current_image_key}"
# Question input for the current image
question = st.text_input("Ask a question about this image:", key=question_key)
# Get Answer button for the current image
if st.button('Get Answer', key=button_key):
# Process the image and question
answer = get_answer(image_info['image'], question) # Implement this function
image_info['qa_history'].append((question, answer))
st.experimental_rerun() # Rerun to update the display
def get_answer(image, question):
# Implement the logic to process the image and question, and return the answer
return "Sample answer based on the image and question."
if __name__ == "__main__":
main()
|