Update app.py

app.py

@@ -11,11 +11,11 @@ from build_vocab import Vocabulary
 
 
 # Caption generation functions
-def generate_caption_clipgpt(image):
+def generate_caption_clipgpt(image, max_tokens, temperature):
     caption = clipGPT.generate_caption_clipgpt(image)
     return caption
 
-def generate_caption_vitgpt(image):
+def generate_caption_vitgpt(image, max_tokens, temperature):
     caption = vitGPT.generate_caption(image)
     return caption
 
@@ -26,11 +26,17 @@ 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>")
 
-       
+    with gr.Row():
+        # ... (your existing image upload components)
+
+        with gr.Column():  # Column for dropdowns and model choice
+            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") 
+
     with gr.Row():
         sample_images = [
         'https://imgur.com/W1pIr9b',
@@ -56,18 +62,18 @@ with gr.Blocks() as demo:
 
     def predict(img, model_name):
         if model_name == "CLIP-GPT2":
-            return generate_caption_clipgpt(img)
+            return generate_caption_clipgpt(img, max_tokens, temperature)
         elif model_name == "ViT-GPT2":
-            return generate_caption_vitgpt(img)
+            return generate_caption_vitgpt(img, max_tokens, temperature)
         elif model_name == "ViT-CoAttention":
             return generate_caption_vitCoAtt(img)
         else:
             return "Caption generation for this model is not yet implemented."     
 
 
-    # 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
+    # Event handlers 
+    generate_button.click(predict, [image, model_choice, max_tokens, temperature], caption) 
+    sample_images_gallery.change(predict, [sample_images_gallery, model_choice, max_tokens, temperature], caption)  
 
 
 demo.launch()