Update app.py

app.py

@@ -2,8 +2,23 @@ import gradio as gr
 from PIL import Image
 import clipGPT
 import vitGPT
-import skimage.io as io
-import PIL.Image
+import difflib
+
+
+def compare_and_highlight(text1, text2):
+    matcher = difflib.SequenceMatcher(None, text1, text2)
+    output = ''
+    for op, a1, a2, b1, b2 in matcher.get_opcodes():
+        if op == 'equal':
+            output += f"**{text1[a1:a2]}**"  # Highlight matches in bold
+        elif op == 'insert':
+            output += f"<ins>{text2[b1:b2]}</ins>" 
+        elif op == 'delete':
+            output += f"<del>{text1[a1:a2]}</del>"
+        elif op == 'replace':  
+            # Handle replacements (more complex)
+            output += f"<del>{text1[a1:a2]}</del> <ins>{text2[b1:b2]}</ins>" 
+    return output
 
 
 # Caption generation functions
@@ -17,44 +32,117 @@ def generate_caption_vitgpt(image):
 
 
 
-with gr.Blocks() as demo:
-    
-
-    gr.HTML("<h1 style='text-align: center;'>MedViT: A Vision Transformer-Driven Method for Generating Medical Reports 🏥🤖</h1>")
-    gr.HTML("<p style='text-align: center;'>You can generate captions by uploading an X-Ray and selecting a model of your choice below</p>")
+# Sample image paths
+sample_images = [
+    "CXR191_IM-0591-1001.jpg",
+    "CXR191_IM-0598-1001.jpg",
+    "CXR191_IM-0601-1001.jpg",
+    "CXR191_IM-0609-1001.jpg",
+    "CXR191_IM-0618-1001.jpg"
+]
 
+# Gradio interface 
+with gr.Blocks() as demo:
     with gr.Row():
-        sample_images = [
-        "CXR191_IM-0591-1001.png",
-        "CXR192_IM-0598-1001.png",
-        "CXR193_IM-0601-1001.png",
-        "CXR194_IM-0609-1001.png",
-        "CXR195_IM-0618-1001.png"
-    ]
-        image = gr.Image(label="Upload Chest X-ray")
-        gr.Gallery(
-            value = sample_images,
-            label="Sample Images",
-        )
-        # sample_images_gallery = gr.Gallery(
-        #     value = sample_images,
-        #     label="Sample Images",
-        # )
-    with gr.Row():
+        image = gr.Image(label="Upload Chest X-ray", source="upload")
+        sample_image_gallery = gr.ImageGallery(sample_images, label="Sample Images")
+    with gr.Row():  
         model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
-        generate_button = gr.Button("Generate Caption") 
-    caption = gr.Textbox(label="Generated Caption") 
+    with gr.Row():
+        caption = gr.Textbox(label="Generated Caption") 
+
+    generated_captions = {  
+    "CLIP-GPT2": "",
+    "ViT-GPT2": "",
+    }
 
     def predict(img, model_name):
         if model_name == "CLIP-GPT2":
-            return generate_caption_clipgpt(img)  
+            return generate_caption_clipgpt(img)
         elif model_name == "ViT-GPT2":
             return generate_caption_vitgpt(img)
         else:
-            return "Caption generation for this model is not yet implemented."
+            return "Caption generation for this model is not yet implemented."     
+        generated_captions[model_name] = caption 
+
+    with gr.Row():
+        caption1 = gr.Textbox(label="CLIP-GPT2")
+        caption2 = gr.Textbox(label="ViT-GPT2")
+        compare_button = gr.Button("Compare Captions")
+    with gr.Row():
+        comparison_result = gr.Textbox(label="Comparison Result")
 
-    generate_button.click(predict, [image, model_choice], caption)  # Trigger prediction on button click 
-    # sample_images_gallery.change(predict, [sample_images_gallery, model_choice], caption)  # Handle sample images
+    # Compare captions on button click
+    compare_button.click(lambda: compare_and_highlight(
+        generated_captions["CLIP-GPT2"], generated_captions["ViT-GPT2"]
+    ), [], comparison_result) 
 
+    # Handle changes for both uploaded and sample images
+    gr.Image.change(predict, [image, model_choice], caption)
+    sample_image_gallery.change(predict, [sample_image_gallery, model_choice], caption)
 
 demo.launch() 
+
+
+
+# import gradio as gr
+# from PIL import Image
+# import clipGPT
+# import vitGPT
+# import skimage.io as io
+# import PIL.Image
+
+
+# # Caption generation functions
+# def generate_caption_clipgpt(image):
+#     caption = clipGPT.generate_caption_clipgpt(image)
+#     return caption
+
+# def generate_caption_vitgpt(image):
+#     caption = vitGPT.generate_caption(image)
+#     return caption
+
+
+
+# with gr.Blocks() as demo:
+    
+
+#     gr.HTML("<h1 style='text-align: center;'>MedViT: A Vision Transformer-Driven Method for Generating Medical Reports 🏥🤖</h1>")
+#     gr.HTML("<p style='text-align: center;'>You can generate captions by uploading an X-Ray and selecting a model of your choice below</p>")
+
+#     with gr.Row():
+#         sample_images = [
+#         "CXR191_IM-0591-1001.png",
+#         "CXR192_IM-0598-1001.png",
+#         "CXR193_IM-0601-1001.png",
+#         "CXR194_IM-0609-1001.png",
+#         "CXR195_IM-0618-1001.png"
+#     ]
+#         image = gr.Image(label="Upload Chest X-ray")
+#         gr.Gallery(
+#             value = sample_images,
+#             label="Sample Images",
+#         )
+#         # sample_images_gallery = gr.Gallery(
+#         #     value = sample_images,
+#         #     label="Sample Images",
+#         # )
+#     with gr.Row():
+#         model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
+#         generate_button = gr.Button("Generate Caption") 
+#     caption = gr.Textbox(label="Generated Caption") 
+
+#     def predict(img, model_name):
+#         if model_name == "CLIP-GPT2":
+#             return generate_caption_clipgpt(img)  
+#         elif model_name == "ViT-GPT2":
+#             return generate_caption_vitgpt(img)
+#         else:
+#             return "Caption generation for this model is not yet implemented."
+
+#     generate_button.click(predict, [image, model_choice], caption)  # Trigger prediction on button click 
+#     # sample_images_gallery.change(predict, [sample_images_gallery, model_choice], caption)  # Handle sample images
+
+
+# demo.launch() 
+