update UI

app.py

@@ -948,6 +948,60 @@ with demo:
             from draft_gradio_app_text import make_demo
         make_demo()
         
+    with gr.Tab('Model Aligned'): 
+        gr.Markdown('This page reproduce the results from the paper [AlignedCut](https://arxiv.org/abs/2406.18344)')
+        gr.Markdown('---')
+        gr.Markdown('**Features are aligned across models and layers.** A linear alignment transform is trained for each model/layer, learning signal comes from 1) fMRI brain activation and 2) segmentation preserving eigen-constraints.')
+        gr.Markdown('NCUT is computed on the concatenated graph of all models, layers, and images. Color is **aligned** across all models and layers.')
+        gr.Markdown('')
+        gr.Markdown("To see a good pattern, you will need to load 100~1000 images. 100 images need 10sec for RTX4090. Running out of HuggingFace GPU Quota? Try [Demo](https://ncut-pytorch.readthedocs.io/en/latest/demo/) hosted at UPenn")
+        gr.Markdown('---')
+        with gr.Row():
+            with gr.Column(scale=5, min_width=200):
+                input_gallery, submit_button, clear_images_button = make_input_images_section()
+
+                dataset_dropdown, num_images_slider, random_seed_slider, load_images_button = make_dataset_images_section(advanced=True)
+                num_images_slider.value = 100
+                
+            with gr.Column(scale=5, min_width=200):
+                gr.Markdown('Model: CLIP(ViT-B-16/openai), DiNOv2reg(dinov2_vitb14_reg), MAE(vit_base)')
+                gr.Markdown('Layer type: attention output (attn), without sum of residual')
+                [
+                    model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
+                    affinity_focal_gamma_slider, num_sample_ncut_slider, knn_ncut_slider, 
+                    embedding_method_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
+                    perplexity_slider, n_neighbors_slider, min_dist_slider, 
+                    sampling_method_dropdown
+                ] = make_parameters_section()
+                model_dropdown.value = "AlignedThreeModelAttnNodes"
+                model_dropdown.visible = False
+                layer_slider.visible = False
+                node_type_dropdown.visible = False
+                # logging text box
+                logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information")
+                
+        galleries = []
+        for i_model, model_name in enumerate(["CLIP", "DINO", "MAE"]):
+            with gr.Row():
+                for i_layer in range(1, 13):
+                    with gr.Column(scale=5, min_width=200):
+                        gr.Markdown(f'### {model_name} Layer {i_layer}')
+                        output_gallery = gr.Gallery(value=[], label="NCUT Embedding", show_label=False, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="auto")
+                        galleries.append(output_gallery)
+                
+
+        clear_images_button.click(lambda x: [] * (len(galleries) + 1), outputs=[input_gallery] + galleries)
+        submit_button.click(
+            run_fn,
+            inputs=[
+                input_gallery, model_dropdown, layer_slider, num_eig_slider, node_type_dropdown, 
+                affinity_focal_gamma_slider, num_sample_ncut_slider, knn_ncut_slider, 
+                embedding_method_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
+                perplexity_slider, n_neighbors_slider, min_dist_slider, sampling_method_dropdown
+            ],
+            outputs=galleries + [logging_text],
+        )
+    
     with gr.Tab('Compare Models'): 
         def add_one_model(i_model=1):
             with gr.Column(scale=5, min_width=200) as col:
@@ -1015,59 +1069,7 @@ with demo:
         buttons[-1].click(fn=lambda x: gr.update(visible=True), outputs=rows[-1])
         buttons[-1].click(fn=lambda x: gr.update(visible=False), outputs=buttons[-1])
     
-    with gr.Tab('Compare (Aligned)'): 
-        gr.Markdown('This page reproduce the results from the paper [AlignedCut](https://arxiv.org/abs/2406.18344)')
-        gr.Markdown('---')
-        gr.Markdown('**Features are aligned across models and layers.** A linear alignment transform is trained for each model/layer, learning signal comes from 1) fMRI brain activation and 2) segmentation preserving eigen-constraints.')
-        gr.Markdown('NCUT is computed on the concatenated graph of all models, layers, and images. Color is **aligned** across all models and layers.')
-        gr.Markdown('')
-        gr.Markdown("To see a good pattern, you will need to load 100~1000 images. 100 images need 10sec for RTX4090. Running out of HuggingFace GPU Quota? Try [Demo](https://ncut-pytorch.readthedocs.io/en/latest/demo/) hosted at UPenn")
-        gr.Markdown('---')
-        with gr.Row():
-            with gr.Column(scale=5, min_width=200):
-                input_gallery, submit_button, clear_images_button = make_input_images_section()
-
-                dataset_dropdown, num_images_slider, random_seed_slider, load_images_button = make_dataset_images_section(advanced=True)
-                num_images_slider.value = 100
-                
-            with gr.Column(scale=5, min_width=200):
-                gr.Markdown('Model: CLIP(ViT-B-16/openai), DiNOv2reg(dinov2_vitb14_reg), MAE(vit_base)')
-                gr.Markdown('Layer type: attention output (attn), without sum of residual')
-                [
-                    model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
-                    affinity_focal_gamma_slider, num_sample_ncut_slider, knn_ncut_slider, 
-                    embedding_method_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
-                    perplexity_slider, n_neighbors_slider, min_dist_slider, 
-                    sampling_method_dropdown
-                ] = make_parameters_section()
-                model_dropdown.value = "AlignedThreeModelAttnNodes"
-                model_dropdown.visible = False
-                layer_slider.visible = False
-                node_type_dropdown.visible = False
-                # logging text box
-                logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information")
-                
-        galleries = []
-        for i_model, model_name in enumerate(["CLIP", "DINO", "MAE"]):
-            with gr.Row():
-                for i_layer in range(1, 13):
-                    with gr.Column(scale=5, min_width=200):
-                        gr.Markdown(f'### {model_name} Layer {i_layer}')
-                        output_gallery = gr.Gallery(value=[], label="NCUT Embedding", show_label=False, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="auto")
-                        galleries.append(output_gallery)
-                
-
-        clear_images_button.click(lambda x: [] * (len(galleries) + 1), outputs=[input_gallery] + galleries)
-        submit_button.click(
-            run_fn,
-            inputs=[
-                input_gallery, model_dropdown, layer_slider, num_eig_slider, node_type_dropdown, 
-                affinity_focal_gamma_slider, num_sample_ncut_slider, knn_ncut_slider, 
-                embedding_method_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
-                perplexity_slider, n_neighbors_slider, min_dist_slider, sampling_method_dropdown
-            ],
-            outputs=galleries + [logging_text],
-        )
+    
     
     with gr.Row():
         with gr.Column():