Update app.py

app.py

@@ -11,47 +11,49 @@ from my_model.captioner.image_captioning import get_caption
 from my_model.utilities import free_gpu_resources
 
 
-    
-
-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
-
-
 
+# Placeholder for undefined functions
+def load_caption_model():
+    st.write("Placeholder for load_caption_model function")
+    return None, None
 
-
-
-    
-
-
-# Set up the sidebar navigation
-st.sidebar.title("Navigation")
-selection = st.sidebar.radio("Go to", ["Home", "Dataset Analysis", "Evaluation Results", "Run Inference", "Dissertation Report", ])
-
-# Set up the main page content based on navigation selection
-if selection == "Home":
-    st.title("MultiModal Learning for Knowledg-Based Visual Question Answering")
+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...")
-    # You can include more content for the home page here
 
-elif selection == "Dissertation Report":
+def display_dissertation_report():
     st.title("Dissertation Report")
     st.write("Click the link below to view the PDF.")
-    # Example to display a link to a PDF
     st.download_button(
         label="Download PDF",
         data=open("Files/Dissertation Report.pdf", "rb"),
@@ -59,133 +61,74 @@ elif selection == "Dissertation Report":
         mime="application/octet-stream"
     )
 
-elif selection == "Evaluation Results":
+def display_evaluation_results():
     st.title("Evaluation Results")
     st.write("This is a Place Holder until the contents are uploaded.")
 
-elif selection == "Dataset Analysis":
+def display_dataset_analysis():
     st.title("OK-VQA Dataset Analysis")
     st.write("This is a Place Holder until the contents are uploaded.")
 
-elif selection == "Run Inference":
-    st.title("Run Inference")
-    st.write("This page allows you to run the space for inference.")
-    # You would include your inference code here
-    # For example, if you have a form to collect user input for the model:
-    user_input = st.text_input("Enter your text here...")
-    if st.button("Run"):
-        # Call your model inference function
-        # result = run_inference(user_input)
-        # st.write(result)
-        pass  # Replace pass with your inference code
-
-# Other pages and functionality would be added in a similar manner.
-
-
-
-
-
-
-
-        
-
-
-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('Generate Caption'):
-    free_gpu_resources()
-    if image is not None:
-        # Display the image
-        st.image(image, use_column_width=True)
-        caption = get_caption(image)
-        st.write(caption)
-        free_gpu_resources()
-
-    else:
-        st.write("Please upload an image and enter a question.")
-        
-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
-
-    processed_image, detected_objects = detect_and_draw_objects(image, model_name, threshold)
-
-    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)
-
-            # Display the original image
-            st.image(image, use_column_width=True, caption="Original Image")
-
-            # Perform object detection
-            processed_image, detected_objects = perform_object_detection(image, detect_model, threshold)
-
-
-            # Display the image with detected objects
-            st.image(processed_image, use_column_width=True, caption="Image with Detected Objects")
-
-            # Display the detected objects as text
-            st.write(detected_objects)
-
-
-        except Exception as e:
-            st.error(f"Error loading image: {e}")
-
-    else:
-        st.write("Please upload an image for object detection.")
-
-
+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()