Update app.py

app.py

@@ -1,3 +1,5 @@
+
+
 import gradio as gr
 from PIL import Image
 import clipGPT
@@ -11,12 +13,12 @@ from build_vocab import Vocabulary
 
 
 # Caption generation functions
-def generate_caption_clipgpt(image, max_tokens, temperature):
-    caption = clipGPT.generate_caption_clipgpt(image, max_tokens, temperature)
+def generate_caption_clipgpt(image):
+    caption = clipGPT.generate_caption_clipgpt(image)
     return caption
 
-def generate_caption_vitgpt(image, max_tokens, temperature):
-    caption = vitGPT.generate_caption(image, max_tokens, temperature)
+def generate_caption_vitgpt(image):
+    caption = vitGPT.generate_caption(image)
     return caption
 
 def generate_caption_vitCoAtt(image):
@@ -26,78 +28,48 @@ def generate_caption_vitCoAtt(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_data = [
-        ['sample/CXR192_IM-0598-1001.png', '75', '0.7', 'CLIP-GPT2, ViT-GPT2, ViT-CoAttention', '...'],
-        ['https://imgur.com/MLJaWnf', '50' ,'0.8', 'CLIP-GPT2, ViT-CoAttention', '...']
-    ]
-
+       
     with gr.Row():
-        image_display = gr.Image(label="Selected Image")  # Area to display the selected image
-        image_table = gr.Dataframe(sample_data, headers=['image', 'max token', 'temp', 'model supported', 'ground truth'], datatype=['str', 'str', 'str', 'str', 'str']) # Changed to 'str'
+        sample_images = [
+        'https://imgur.com/W1pIr9b',
+        'https://imgur.com/MLJaWnf',
+        'https://imgur.com/6XymFW1',
+        'https://imgur.com/zdPjZZ1',
+        'https://imgur.com/DKUlZbF'
+            ]
+
+        
+        image = gr.Image(label="Upload Chest X-ray", type="pil")    
+        
+        sample_images_gallery = gr.Gallery(value = sample_images,label="Sample Images")
 
     with gr.Row():
-        image = gr.Image(label="Upload Chest X-ray", type="pil")  
+        model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
 
+        generate_button = gr.Button("Generate Caption") 
     
-    gr.HTML("<p style='text-align: center;'> Please select the Number of Max Tokens and Temperature setting, if you are testing CLIP GPT2 and VIT GPT2 Models</p>")
-
-    with gr.Row():
-        with gr.Column(): 
-            max_tokens = gr.Dropdown(list(range(50, 101)), label="Max Tokens", value=75)
-            temperature = gr.Slider(0.5, 0.9, step=0.1, label="Temperature", value=0.7) 
-        
-        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, max_tokens, temperature):
+    def predict(img, model_name):
         if model_name == "CLIP-GPT2":
-            return generate_caption_clipgpt(img, max_tokens, temperature)
+            return generate_caption_clipgpt(img)
         elif model_name == "ViT-GPT2":
-            return generate_caption_vitgpt(img, max_tokens, temperature)
+            return generate_caption_vitgpt(img)
         elif model_name == "ViT-CoAttention":
             return generate_caption_vitCoAtt(img)
         else:
-            return "Caption generation for this model is not yet implemented."  
+            return "Caption generation for this model is not yet implemented."     
 
-    def predict_from_table(row, model_name):  
-        img_url = row['image']
-        max_tokens = row['max token']
-        temperature = row['temp']
-        
-        image_display.update(value=img_url)  # Update the image display
-    
-        # Load the image
-        img = Image.open(io.imread(img_url))
-    
-        # Generate the caption
-        if model_name == "CLIP-GPT2":
-            caption = generate_caption_clipgpt(img, max_tokens, temperature) 
-        elif model_name == "ViT-GPT2":
-            caption = generate_caption_vitgpt(img, max_tokens, temperature)
-        elif model_name == "ViT-CoAttention":
-            caption = generate_caption_vitCoAtt(img)
-        else:
-            caption = "Caption generation for this model is not yet implemented."
-    
-        return image_display, caption  # Return both the image and the caption
-
-    # Event handlers 
-    generate_button.click(predict, [image, model_choice, max_tokens, temperature], caption) 
 
-    # Create an event handler for the entire Dataframe
-    def dataframe_selected(index, row, model_choice):
-        if row is not None:  # Check if an actual row was selected
-            return predict_from_table(row, model_choice)
-    
-    # Attach the function to the dataframe
-    image_table.change(dataframe_selected, inputs=[image_table, model_choice], outputs=[image_display, caption])
-    
+    # Event handlers
+    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()