Update app.py

app.py

@@ -10,22 +10,7 @@ from my_model.captioner.image_captioning import get_caption
 from my_model.utilities import free_gpu_resources
 
 
-def perform_object_detection(image, model_name, threshold=0.2):
-    """
-    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.
-    """
-
-    processed_image, detected_objects = detect_and_draw_objects(image, model_name, threshold)
-
-    return processed_image, detected_objects
-
-    
+
 # Placeholder for undefined functions
 def load_caption_model():
     st.write("Placeholder for load_caption_model function")
@@ -34,9 +19,6 @@ def load_caption_model():
 def answer_question(image, question, model, processor):
     return "Placeholder answer for the question"
 
-def detect_and_draw_objects(image, model_name, threshold):
-    perform_object_detection()
-
 def get_caption(image):
     return "Generated caption for the image"
 
@@ -44,50 +26,12 @@ def free_gpu_resources():
     pass
 
 # Sample images (assuming these are paths to your sample images)
-sample_images = ["Files/sample1.jpg", "Files/sample2.jpg", "Files/sample3.jpg", "Files/sample4.jpg", "Files/sample5.jpg", "Files/sample6.jpg", "Files/sample7.jpg"]
-
-# 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":
-        st.title("MultiModal Learning for Knowledg-Based Visual Question Answering")
-        st.write("Home page content goes here...")
-        
-    elif selection == "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"),
-            file_name="example.pdf",
-            mime="application/octet-stream"
-        )
-
-        
-    elif selection == "Evaluation Results":
-        st.title("Evaluation Results")
-        st.write("This is a Place Holder until the contents are uploaded.")
-
-        
-    elif selection == "Dataset Analysis":
-        st.title("OK-VQA Dataset Analysis")
-        st.write("This is a Place Holder until the contents are uploaded.")
-
-
-    elif selection == "Run Inference":
-        run_inference()
-            
-    elif selection == "Object Detection":
-        run_object_detection()
-
-# Other display functions...
+sample_images = ["Files/sample1.jpg", "Files/sample2.jpg", "Files/sample3.jpg", 
+                 "Files/sample4.jpg", "Files/sample5.jpg", "Files/sample6.jpg", 
+                 "Files/sample7.jpg"]
 
 def run_inference():
     st.title("Run Inference")
-    # Image-based Q&A and Object Detection functionality
     image_qa_and_object_detection()
 
 def image_qa_and_object_detection():
@@ -109,12 +53,8 @@ def image_qa_app():
         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)
-        process_uploaded_image(image)
 
     # Display sample images
     st.write("Or choose from sample images:")
@@ -123,16 +63,48 @@ def image_qa_app():
             uploaded_image = Image.open(sample_image_path)
             process_uploaded_image(uploaded_image)
 
+    if uploaded_image is not None:
+        image = Image.open(uploaded_image)
+        process_uploaded_image(image)
+
 def process_uploaded_image(image):
     current_image_key = image.filename  # Use image filename as a unique key
-    # ... rest of the image processing code ...
+    # 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 = answer_question(image_info['image'], question, None, None)  # Implement this function
+                image_info['qa_history'].append((question, answer))
+                st.experimental_rerun()  # Rerun to update the display
 
 # Object Detection App
 def object_detection_app():
     # ... Implement your code for object detection ...
     pass
 
-# Other functions...
+# Main function and other display functions...
 
 if __name__ == "__main__":
     main()