update playground

app.py

@@ -1702,7 +1702,7 @@ def load_and_append(existing_images, *args, **kwargs):
     gr.Info(f"Total images: {len(existing_images)}")
     return existing_images
 
-def make_input_images_section(rows=1, cols=3, height="auto", advanced=False, is_random=False, allow_download=False, markdown=True, n_example_images=100):
+def make_input_images_section(rows=1, cols=3, height="450px", advanced=False, is_random=False, allow_download=False, markdown=True, n_example_images=100):
     if markdown:
         gr.Markdown('### Input Images')
     input_gallery = gr.Gallery(value=None, label="Input images", show_label=True, elem_id="input_images", columns=[cols], rows=[rows], object_fit="contain", height=height, type="pil", show_share_button=False,
@@ -1750,7 +1750,7 @@ def make_input_images_section(rows=1, cols=3, height="auto", advanced=False, is_
             # ("CatDog", ['./images/catdog1.jpg', './images/catdog2.jpg', './images/catdog3.jpg'], "microsoft/cats_vs_dogs"),
             # ("Bird", ['./images/bird1.jpg', './images/bird2.jpg', './images/bird3.jpg'], "Multimodal-Fatima/CUB_train"),
             # ("ChestXray", ['./images/chestxray1.jpg', './images/chestxray2.jpg', './images/chestxray3.jpg'], "hongrui/mimic_chest_xray_v_1"),
-            ("BrainMRI", ['./images/brain1.jpg', './images/brain2.jpg', './images/brain3.jpg'], "sartajbhuvaji/Brain-Tumor-Classification"),
+            ("MRI", ['./images/brain1.jpg', './images/brain2.jpg', './images/brain3.jpg'], "sartajbhuvaji/Brain-Tumor-Classification"),
             ("Kanji", ['./images/kanji1.jpg', './images/kanji2.jpg', './images/kanji3.jpg'], "yashvoladoddi37/kanjienglish"),
         ]
         for name, images, dataset_name in example_items:
@@ -2073,7 +2073,7 @@ def add_download_button(gallery, filename_prefix="output"):
 def make_output_images_section(markdown=True, button=True):
     if markdown:
         gr.Markdown('### Output Images')
-    output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, interactive=False)
+    output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, interactive=False)
     if button:
         add_rotate_flip_buttons(output_gallery)
     return output_gallery
@@ -2202,7 +2202,7 @@ with demo:
             with gr.Column(scale=5, min_width=200):
                 # gr.Markdown("### Step 2a: Run Backbone and NCUT")
                 # with gr.Accordion(label="Backbone Parameters", visible=True, open=False):
-                output_gallery = gr.Gallery(format='png', value=[], label="NCUT spectral-tSNE", show_label=True, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, interactive=False)
+                output_gallery = gr.Gallery(format='png', value=[], label="NCUT spectral-tSNE", show_label=True, elem_id="ncut", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, interactive=False)
                 def add_rotate_flip_buttons_with_state(output_gallery, tsne3d_rgb):
                     with gr.Row():
                         rotate_button = gr.Button("🔄 Rotate", elem_id="rotate_button", variant='secondary')
@@ -2414,7 +2414,7 @@ with demo:
                 gr.Markdown("Known Issue: Resize the browser window will break the clicking, please refresh the page.")
                 with gr.Accordion("Outputs", open=True):
                     gr.Markdown("""
-                                1. spectral-tSNE tree: ◆ marker is the N points, connected components to the clicked dot.
+                                1. spectral-tSNE tree: ◆ marker is the N points, connected components to the clicked .
                                 2. Cluster Heatmap: max of N cosine similarity to N points in the connected components.
                                 """)
             with gr.Column(scale=5, min_width=200): 
@@ -2448,8 +2448,10 @@ with demo:
                 with gr.Column(scale=5, min_width=200):
                     output_tree_image = gr.Image(label=f"spectral-tSNE tree [row#{i_row}]", elem_id="output_image", interactive=False)
                     text_block = gr.Textbox("", label="Logging", elem_id=f"logging_{i_row}", type="text", placeholder="Logging information", autofocus=False, autoscroll=False, lines=2, show_label=False)
+                    delete_button = gr.Button("❌ Delete", elem_id=f"delete_button_{i_row}", variant='secondary')
                 with gr.Column(scale=10, min_width=200):
-                    heatmap_gallery = gr.Gallery(format='png', value=[], label=f"Cluster Heatmap [row#{i_row}]", show_label=True, elem_id="heatmap", columns=[6], rows=[1], object_fit="contain", height="auto", show_share_button=True, interactive=False)
+                    heatmap_gallery = gr.Gallery(format='png', value=[], label=f"Cluster Heatmap [row#{i_row}]", show_label=True, elem_id="heatmap", columns=[6], rows=[1], object_fit="contain", height="500px", show_share_button=True, interactive=False)
+            delete_button.click(lambda: gr.update(visible=False), outputs=[inspect_output_row])
             return inspect_output_row, output_tree_image, heatmap_gallery, text_block
         
         gr.Markdown('---')
@@ -2600,6 +2602,193 @@ with demo:
             outputs=inspect_output_rows + output_tree_images + heatmap_galleries + text_blocks + [current_output_row, inspect_logging_text],
         )
         
+    with gr.Tab('PlayGround (eig)', visible=True) as test_playground_tab2:
+        eigvecs = gr.State(np.array([]))
+        with gr.Row():
+            with gr.Column(scale=5, min_width=200):
+                gr.Markdown("### Step 1: Load Images")
+                input_gallery, submit_button, clear_images_button, dataset_dropdown, num_images_slider, random_seed_slider, load_images_button = make_input_images_section(n_example_images=10)
+                submit_button.visible = False
+                num_images_slider.value = 30
+                
+                false_placeholder = gr.Checkbox(label="False", value=False, elem_id="false_placeholder", visible=False)
+                no_prompt = gr.Textbox("", label="", elem_id="empty_placeholder", type="text", placeholder="", visible=False)
+                
+                
+            with gr.Column(scale=5, min_width=200):
+                gr.Markdown("### Step 2a: Run Backbone and NCUT")
+                with gr.Accordion(label="Backbone Parameters", visible=True, open=False):
+                    [
+                        model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
+                        affinity_focal_gamma_slider, num_sample_ncut_slider, ncut_knn_slider, ncut_indirect_connection, ncut_make_orthogonal, 
+                        embedding_method_dropdown, embedding_metric_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
+                        perplexity_slider, n_neighbors_slider, min_dist_slider, 
+                        sampling_method_dropdown, ncut_metric_dropdown, positive_prompt, negative_prompt
+                    ] = make_parameters_section(ncut_parameter_dropdown=False, tsne_parameter_dropdown=False)
+                    num_eig_slider.value = 1024
+                    num_eig_slider.visible = False
+                submit_button = gr.Button("🔴 RUN NCUT", elem_id="run_ncut", variant='primary')
+                logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information", autofocus=False, autoscroll=False)
+                submit_button.click(
+                    partial(run_fn, n_ret=1, only_eigvecs=True),
+                    inputs=[
+                        input_gallery, model_dropdown, layer_slider, num_eig_slider, node_type_dropdown, 
+                        positive_prompt, negative_prompt,
+                        false_placeholder, no_prompt, no_prompt, no_prompt,
+                        affinity_focal_gamma_slider, num_sample_ncut_slider, ncut_knn_slider, ncut_indirect_connection, ncut_make_orthogonal, 
+                        embedding_method_dropdown, embedding_metric_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
+                        perplexity_slider, n_neighbors_slider, min_dist_slider, sampling_method_dropdown, ncut_metric_dropdown
+                    ],
+                    outputs=[eigvecs, logging_text],
+                )
+                gr.Markdown("### Step 2b: Pick an Image and Draw a Point")
+                from gradio_image_prompter import ImagePrompter
+                image1_slider = gr.Slider(0, 0, step=1, label="Image#1 Index", value=0, elem_id="image1_slider", interactive=True)
+                load_one_image_button = gr.Button("🔴 Load Image", elem_id="load_one_image_button", variant='primary')
+                gr.Markdown("""
+                    <h5>
+                    🖱️ Left Click: Foreground </br>
+                    </h5>
+                """)
+                prompt_image1 = ImagePrompter(show_label=False, elem_id="prompt_image1", interactive=False)
+                def update_prompt_image(original_images, index):
+                    images = original_images
+                    if images is None:
+                        return gr.update()
+                    total_len = len(images)
+                    if total_len == 0:
+                        return gr.update()
+                    if index >= total_len:
+                        index = total_len - 1
+                    return gr.update(value={'image': images[index][0], 'points': []}, interactive=True)
+                load_one_image_button.click(update_prompt_image, inputs=[input_gallery, image1_slider], outputs=[prompt_image1])
+                input_gallery.change(update_prompt_image, inputs=[input_gallery, image1_slider], outputs=[prompt_image1])
+                input_gallery.change(fn=lambda x: gr.update(maximum=len(x)-1), inputs=[input_gallery], outputs=[image1_slider])
+                image1_slider.change(update_prompt_image, inputs=[input_gallery, image1_slider], outputs=[prompt_image1])
+                
+            child_idx = gr.State([])
+            current_idx = gr.State(None)
+            n_eig = gr.State(64)
+            with gr.Column(scale=5, min_width=200):
+                gr.Markdown("### Step 3: Check groupping")
+                child_distance_slider = gr.Slider(0, 0.5, step=0.001, label="Child Distance", value=0.1, elem_id="child_distance_slider", interactive=True)
+                child_distance_slider.visible = False
+                overlay_image_checkbox = gr.Checkbox(label="Overlay Image", value=True, elem_id="overlay_image_checkbox", interactive=True)
+                n_eig_slider = gr.Slider(0, 1024, step=1, label="Number of Eigenvectors", value=256, elem_id="n_eig_slider", interactive=True)
+                run_button = gr.Button("🔴 RUN", elem_id="run_groupping", variant='primary')
+                gr.Markdown("1. 🔴 RUN </br>2. repeat: [+num_eigvecs] / [-num_eigvecs]")
+                with gr.Row():
+                    doublue_eigs_button = gr.Button("[+num_eigvecs]", elem_id="doublue_eigs_button", variant='secondary')
+                    half_eigs_button = gr.Button("[-num_eigvecs]", elem_id="half_eigs_button", variant='secondary')
+                current_plot = gr.Gallery(value=None, label="Current", show_label=True, elem_id="current_plot", interactive=False, rows=[1], columns=[2])
+    
+        def relative_xy(prompts):
+            image = prompts['image']
+            points = np.asarray(prompts['points'])
+            if points.shape[0] == 0:
+                return [], []
+            is_point = points[:, 5] == 4.0
+            points = points[is_point]
+            is_positive = points[:, 2] == 1.0
+            is_negative = points[:, 2] == 0.0
+            xy = points[:, :2].tolist()
+            if isinstance(image, str):
+                image = Image.open(image)
+                image = np.array(image)
+            h, w = image.shape[:2]
+            new_xy = [(x/w, y/h) for x, y in xy]
+            # print(new_xy)
+            return new_xy, is_positive
+        
+        def xy_eigvec(prompts, image_idx, eigvecs):
+            eigvec = eigvecs[image_idx]
+            xy, is_positive = relative_xy(prompts)
+            for i, (x, y) in enumerate(xy):
+                if not is_positive[i]:
+                    continue
+                x = int(x * eigvec.shape[1])
+                y = int(y * eigvec.shape[0])
+                return eigvec[y, x], (y, x)
+        
+        from ncut_pytorch.ncut_pytorch import _transform_heatmap
+        def _run_heatmap_fn(images, eigvecs, prompt_image_idx, prompt_points, n_eig, flat_idx=None, raw_heatmap=False, overlay_image=True):
+            left = eigvecs[..., :n_eig]
+            if flat_idx is not None:
+                right = eigvecs.reshape(-1, eigvecs.shape[-1])[flat_idx]
+                y, x = None, None
+            else:
+                right, (y, x) = xy_eigvec(prompt_points, prompt_image_idx, eigvecs)
+            right = right[:n_eig]
+            left = F.normalize(left, p=2, dim=-1)
+            _right = F.normalize(right, p=2, dim=-1)
+            heatmap = left @ _right.unsqueeze(-1)
+            heatmap = heatmap.squeeze(-1)
+            # heatmap = 1 - heatmap
+            # heatmap = _transform_heatmap(heatmap)
+            if raw_heatmap:
+                return heatmap
+            # apply hot colormap and covert to PIL image 256x256
+            # gr.Info(f"heatmap vmin: {heatmap.min()}, vmax: {heatmap.max()}, mean: {heatmap.mean()}")
+            heatmap = heatmap.cpu().numpy()
+            hot_map = matplotlib.colormaps['hot']
+            heatmap = hot_map(heatmap)
+            pil_images = to_pil_images(torch.tensor(heatmap), target_size=256, force_size=True)
+            if overlay_image:
+                overlaied_images = []
+                for i_image in range(len(images)):
+                    rgb_image = images[i_image].resize((256, 256))
+                    rgb_image = np.array(rgb_image)
+                    heatmap_image = np.array(pil_images[i_image])[..., :3]
+                    blend_image = 0.5 * rgb_image + 0.5 * heatmap_image
+                    blend_image = Image.fromarray(blend_image.astype(np.uint8))
+                    overlaied_images.append(blend_image)
+                pil_images = overlaied_images
+            return pil_images, (y, x)
+
+        @torch.no_grad()
+        def run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx=None, overlay_image=True):
+            gr.Info(f"current number of eigenvectors: {n_eig}", 2)
+            eigvecs = torch.tensor(eigvecs)
+            image1_slider = min(image1_slider, len(images)-1)
+            images = [image[0] for image in images]
+            if isinstance(images[0], str):
+                images = [Image.open(image[0]).convert("RGB").resize((256, 256)) for image in images]
+                        
+            current_heatmap, (y, x) = _run_heatmap_fn(images, eigvecs, image1_slider, prompt_image1, n_eig, flat_idx, overlay_image=overlay_image)
+            
+            return current_heatmap
+        
+        def doublue_eigs_wrapper(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx=None, overlay_image=True):
+            n_eig = int(n_eig*2)
+            n_eig = min(n_eig, eigvecs.shape[-1])
+            n_eig = max(n_eig, 1)
+            return gr.update(value=n_eig), run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx, overlay_image=overlay_image)
+                
+        def half_eigs_wrapper(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, current_idx=None, overlay_image=True):
+            n_eig = int(n_eig/2)
+            n_eig = min(n_eig, eigvecs.shape[-1])
+            n_eig = max(n_eig, 1)
+            return gr.update(value=n_eig), run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, current_idx, overlay_image=overlay_image)
+                
+        none_placeholder = gr.State(None)
+        run_button.click(
+            run_heatmap,
+            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, none_placeholder, overlay_image_checkbox],
+            outputs=[current_plot],
+        )
+        
+        doublue_eigs_button.click(
+            doublue_eigs_wrapper,
+            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, none_placeholder, overlay_image_checkbox],
+            outputs=[n_eig_slider, current_plot],
+        )
+        
+        half_eigs_button.click(
+            half_eigs_wrapper,
+            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, current_idx, overlay_image_checkbox],
+            outputs=[n_eig_slider, current_plot],
+        )
+        
     with gr.Tab('AlignedCut'):
 
         with gr.Row():
@@ -2610,7 +2799,7 @@ with demo:
                 
             with gr.Column(scale=5, min_width=200):
                 output_gallery = make_output_images_section()
-                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[2], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                # cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[2], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
                 [
                     model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
                     affinity_focal_gamma_slider, num_sample_ncut_slider, ncut_knn_slider, ncut_indirect_connection, ncut_make_orthogonal, 
@@ -2623,7 +2812,7 @@ with demo:
         no_prompt = gr.Textbox("", label="", elem_id="empty_placeholder", type="text", placeholder="", visible=False)
         
         submit_button.click(
-            partial(run_fn, n_ret=2, plot_clusters=True),
+            partial(run_fn, n_ret=1, plot_clusters=False),
             inputs=[
                 input_gallery, model_dropdown, layer_slider, num_eig_slider, node_type_dropdown, 
                 positive_prompt, negative_prompt,
@@ -2632,7 +2821,7 @@ with demo:
                 embedding_method_dropdown, embedding_metric_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
                 perplexity_slider, n_neighbors_slider, min_dist_slider, sampling_method_dropdown, ncut_metric_dropdown
             ],
-            outputs=[output_gallery, cluster_gallery, logging_text],
+            outputs=[output_gallery, logging_text],
             api_name="API_AlignedCut",
             scroll_to_output=True,
         )
@@ -2648,9 +2837,9 @@ with demo:
             with gr.Column(scale=5, min_width=200):
                 output_gallery = make_output_images_section()
                 add_download_button(output_gallery, "ncut_embed")
-                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(norm_gallery, "eig_norm")
-                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(cluster_gallery, "clusters")
                 [
                     model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
@@ -2740,7 +2929,7 @@ with demo:
             api_name="API_NCut",
         )
         
-    with gr.Tab('Recursive Cut'): 
+    with gr.Tab('RecursiveCut'): 
         gr.Markdown('NCUT can be applied recursively, the eigenvectors from previous iteration is the input for the next iteration NCUT. ')
         gr.Markdown('__Recursive NCUT__ can amplify or weaken the connections, depending on the `affinity_focal_gamma` setting, please see [Documentation](https://ncut-pytorch.readthedocs.io/en/latest/how_to_get_better_segmentation/#recursive-ncut)')
                 
@@ -2753,15 +2942,15 @@ with demo:
                 logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information")
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #1)')
-                l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l1_gallery)
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #2)')
-                l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l2_gallery)
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #3)')
-                l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l3_gallery)
         with gr.Row():
                 
@@ -2809,7 +2998,7 @@ with demo:
             api_name="API_RecursiveCut"
         )
         
-    with gr.Tab('Recursive Cut (Advanced)', visible=False) as tab_recursivecut_advanced:
+    with gr.Tab('RecursiveCut (Advanced)', visible=False) as tab_recursivecut_advanced:
 
         with gr.Row():
             with gr.Column(scale=5, min_width=200):
@@ -2818,30 +3007,30 @@ with demo:
                 logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information", lines=20)
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #1)')
-                l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l1_gallery)
                 add_download_button(l1_gallery, "ncut_embed_recur1")
-                l1_norm_gallery = gr.Gallery(value=[], label="Recursion #1 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                l1_norm_gallery = gr.Gallery(value=[], label="Recursion #1 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(l1_norm_gallery, "eig_norm_recur1")
-                l1_cluster_gallery = gr.Gallery(value=[], label="Recursion #1 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='auto', show_share_button=True, preview=False, interactive=False)
+                l1_cluster_gallery = gr.Gallery(value=[], label="Recursion #1 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='450px', show_share_button=True, preview=False, interactive=False)
                 add_download_button(l1_cluster_gallery, "clusters_recur1")
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #2)')
-                l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l2_gallery)
                 add_download_button(l2_gallery, "ncut_embed_recur2")
-                l2_norm_gallery = gr.Gallery(value=[], label="Recursion #2 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                l2_norm_gallery = gr.Gallery(value=[], label="Recursion #2 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(l2_norm_gallery, "eig_norm_recur2")
-                l2_cluster_gallery = gr.Gallery(value=[], label="Recursion #2 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='auto', show_share_button=True, preview=False, interactive=False)
+                l2_cluster_gallery = gr.Gallery(value=[], label="Recursion #2 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='450px', show_share_button=True, preview=False, interactive=False)
                 add_download_button(l2_cluster_gallery, "clusters_recur2")
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Recursion #3)')
-                l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_rotate_flip_buttons(l3_gallery)
                 add_download_button(l3_gallery, "ncut_embed_recur3")
-                l3_norm_gallery = gr.Gallery(value=[], label="Recursion #3 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                l3_norm_gallery = gr.Gallery(value=[], label="Recursion #3 Eigenvector Magnitude", show_label=True, elem_id="eig_norm", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(l3_norm_gallery, "eig_norm_recur3")
-                l3_cluster_gallery = gr.Gallery(value=[], label="Recursion #3 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='auto', show_share_button=True, preview=False, interactive=False)
+                l3_cluster_gallery = gr.Gallery(value=[], label="Recursion #3 Clusters", show_label=True, elem_id="clusters", columns=[2], rows=[4], object_fit="contain", height='450px', show_share_button=True, preview=False, interactive=False)
                 add_download_button(l3_cluster_gallery, "clusters_recur3")
         
         with gr.Row():        
@@ -2889,7 +3078,7 @@ with demo:
         )
 
         
-    with gr.Tab('Video'): 
+    with gr.Tab('Video', visible=True) as tab_video:
         with gr.Row():
             with gr.Column(scale=5, min_width=200):
                 video_input_gallery, submit_button, clear_video_button, max_frame_number = make_input_video_section()
@@ -2937,7 +3126,7 @@ with demo:
             from draft_gradio_app_text import make_demo
         make_demo()
         
-    with gr.Tab('Vision-Language'):
+    with gr.Tab('Vision-Language', visible=False) as tab_lisa:
         gr.Markdown('[LISA](https://arxiv.org/pdf/2308.00692) is a vision-language model. Input a text prompt and image, LISA generate segmentation masks.')
         gr.Markdown('In the mask decoder layers, LISA updates the image features w.r.t. the text prompt')
         gr.Markdown('This page aims to see how the text prompt affects the image features')
@@ -2946,15 +3135,15 @@ with demo:
         with gr.Row():
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Prompt #1)')
-                l1_gallery = gr.Gallery(format='png', value=[], label="Prompt #1", show_label=False, elem_id="ncut_p1", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l1_gallery = gr.Gallery(format='png', value=[], label="Prompt #1", show_label=False, elem_id="ncut_p1", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 prompt1 = gr.Textbox(label="Input Prompt #1", elem_id="prompt1", value="where is the person, include the clothes, don't include the guitar and chair", lines=3)
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Prompt #2)')
-                l2_gallery = gr.Gallery(format='png', value=[], label="Prompt #2", show_label=False, elem_id="ncut_p2", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l2_gallery = gr.Gallery(format='png', value=[], label="Prompt #2", show_label=False, elem_id="ncut_p2", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 prompt2 = gr.Textbox(label="Input Prompt #2", elem_id="prompt2", value="where is the Gibson Les Pual guitar", lines=3)
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown('### Output (Prompt #3)')
-                l3_gallery = gr.Gallery(format='png', value=[], label="Prompt #3", show_label=False, elem_id="ncut_p3", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                l3_gallery = gr.Gallery(format='png', value=[], label="Prompt #3", show_label=False, elem_id="ncut_p3", columns=[3], rows=[5], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 prompt3 = gr.Textbox(label="Input Prompt #3", elem_id="prompt3", value="where is the floor", lines=3)
                 
         with gr.Row():
@@ -2986,7 +3175,7 @@ with demo:
             outputs=galleries + [logging_text],
         )
                 
-    with gr.Tab('Model Aligned'): 
+    with gr.Tab('Model Aligned', visible=False) as tab_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.')
@@ -3049,30 +3238,17 @@ with demo:
         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):
-        #         gr.Markdown('### Output (Recursion #1)')
-        #         l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=False, elem_id="ncut_l1", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
-        #         add_output_images_buttons(l1_gallery)
-        #     with gr.Column(scale=5, min_width=200):
-        #         gr.Markdown('### Output (Recursion #2)')
-        #         l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=False, elem_id="ncut_l2", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
-        #         add_output_images_buttons(l2_gallery)
-        #     with gr.Column(scale=5, min_width=200):
-        #         gr.Markdown('### Output (Recursion #3)')
-        #         l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=False, elem_id="ncut_l3", columns=[3], rows=[5], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
-        #         add_output_images_buttons(l3_gallery)    
+ 
         gr.Markdown('### Output (Recursion #1)')
-        l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[100], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False, preview=True)
+        l1_gallery = gr.Gallery(format='png', value=[], label="Recursion #1", show_label=True, elem_id="ncut_l1", columns=[100], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False, preview=True)
         add_rotate_flip_buttons(l1_gallery)
         add_download_button(l1_gallery, "modelaligned_recur1")
         gr.Markdown('### Output (Recursion #2)')
-        l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[100], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False, preview=True)
+        l2_gallery = gr.Gallery(format='png', value=[], label="Recursion #2", show_label=True, elem_id="ncut_l2", columns=[100], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False, preview=True)
         add_rotate_flip_buttons(l2_gallery)
         add_download_button(l2_gallery, "modelaligned_recur2")
         gr.Markdown('### Output (Recursion #3)')
-        l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[100], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False, preview=True)
+        l3_gallery = gr.Gallery(format='png', value=[], label="Recursion #3", show_label=True, elem_id="ncut_l3", columns=[100], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False, preview=True)
         add_rotate_flip_buttons(l3_gallery)  
         add_download_button(l3_gallery, "modelaligned_recur3")
     
@@ -3141,7 +3317,7 @@ with demo:
         def add_one_model(i_model=1):
             with gr.Column(scale=5, min_width=200) as col:
                 gr.Markdown(f'### Output Images')
-                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=False, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=False, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 submit_button = gr.Button("🔴 RUN", elem_id=f"submit_button{i_model}", variant='primary')
                 add_rotate_flip_buttons(output_gallery)
                 [
@@ -3248,16 +3424,16 @@ with demo:
         def add_one_model(i_model=1):
             with gr.Column(scale=5, min_width=200) as col:
                 gr.Markdown(f'### Output Images')
-                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 submit_button = gr.Button("🔴 RUN", elem_id=f"submit_button{i_model}", variant='primary')
                 add_rotate_flip_buttons(output_gallery)
                 add_download_button(output_gallery, f"ncut_embed")
-                mlp_gallery = gr.Gallery(format='png', value=[], label="MLP color align", show_label=True, elem_id=f"mlp{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                mlp_gallery = gr.Gallery(format='png', value=[], label="MLP color align", show_label=True, elem_id=f"mlp{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_mlp_fitting_buttons(output_gallery, mlp_gallery)
                 add_download_button(mlp_gallery, f"mlp_color_align")
-                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id=f"eig_norm{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id=f"eig_norm{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(norm_gallery, f"eig_norm")
-                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id=f"clusters{i_model}", columns=[2], rows=[4], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id=f"clusters{i_model}", columns=[2], rows=[4], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(cluster_gallery, f"clusters")
                 [
                     model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
@@ -3463,16 +3639,16 @@ with demo:
         def add_one_model(i_model=1):
             with gr.Column(scale=5, min_width=200) as col:
                 gr.Markdown(f'### Output Images')
-                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                output_gallery = gr.Gallery(format='png', value=[], label="NCUT Embedding", show_label=True, elem_id=f"ncut{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 submit_button = gr.Button("🔴 RUN", elem_id=f"submit_button{i_model}", variant='primary')
                 add_rotate_flip_buttons(output_gallery)
                 add_download_button(output_gallery, f"ncut_embed")
-                mlp_gallery = gr.Gallery(format='png', value=[], label="MLP color align", show_label=True, elem_id=f"mlp{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_fullscreen_button=True, interactive=False)
+                mlp_gallery = gr.Gallery(format='png', value=[], label="MLP color align", show_label=True, elem_id=f"mlp{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_fullscreen_button=True, interactive=False)
                 add_mlp_fitting_buttons(output_gallery, mlp_gallery)
                 add_download_button(mlp_gallery, f"mlp_color_align")
-                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id=f"eig_norm{i_model}", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                norm_gallery = gr.Gallery(value=[], label="Eigenvector Magnitude", show_label=True, elem_id=f"eig_norm{i_model}", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(norm_gallery, f"eig_norm")
-                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id=f"clusters{i_model}", columns=[2], rows=[4], object_fit="contain", height="auto", show_share_button=True, preview=False, interactive=False)
+                cluster_gallery = gr.Gallery(value=[], label="Clusters", show_label=True, elem_id=f"clusters{i_model}", columns=[2], rows=[4], object_fit="contain", height="450px", show_share_button=True, preview=False, interactive=False)
                 add_download_button(cluster_gallery, f"clusters")
                 [
                     model_dropdown, layer_slider, node_type_dropdown, node_type_dropdown2, head_index_text, make_symmetric, num_eig_slider, 
@@ -3655,7 +3831,7 @@ with demo:
                 
             with gr.Column(scale=5, min_width=200):
                 gr.Markdown("### Step 3: Segment and Crop")
-                mask_gallery = gr.Gallery(value=[], label="Segmentation Masks", show_label=True, elem_id="mask_gallery", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, interactive=False)
+                mask_gallery = gr.Gallery(value=[], label="Segmentation Masks", show_label=True, elem_id="mask_gallery", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, interactive=False)
                 run_crop_button = gr.Button("🔴 RUN", elem_id="run_crop_button", variant='primary')
                 add_download_button(mask_gallery, "mask")
                 distance_threshold_slider = gr.Slider(0, 1, step=0.01, label="Mask Threshold (FG)", value=0.9, elem_id="distance_threshold", info="increase for smaller FG mask")
@@ -3665,7 +3841,7 @@ with demo:
                 overlay_image_checkbox = gr.Checkbox(label="Overlay Original Image", value=True, elem_id="overlay_image_checkbox")
                 # filter_small_area_checkbox = gr.Checkbox(label="Noise Reduction", value=True, elem_id="filter_small_area_checkbox")
                 distance_power_slider = gr.Slider(-3, 3, step=0.01, label="Distance Power", value=0.5, elem_id="distance_power", info="d = d^p", visible=False)
-                crop_gallery = gr.Gallery(value=[], label="Cropped Images", show_label=True, elem_id="crop_gallery", columns=[3], rows=[1], object_fit="contain", height="auto", show_share_button=True, interactive=False)
+                crop_gallery = gr.Gallery(value=[], label="Cropped Images", show_label=True, elem_id="crop_gallery", columns=[3], rows=[1], object_fit="contain", height="450px", show_share_button=True, interactive=False)
                 add_download_button(crop_gallery, "cropped")
                 crop_expand_slider = gr.Slider(1.0, 2.0, step=0.1, label="Crop bbox Expand Factor", value=1.0, elem_id="crop_expand", info="increase for larger crop", visible=True)
                 area_threshold_slider = gr.Slider(0, 100, step=0.1, label="Area Threshold (%)", value=3, elem_id="area_threshold", info="for noise filtering (area of connected components)", visible=False)
@@ -4143,192 +4319,6 @@ with demo:
                 outputs=[n_eig, current_idx, parent_plot, current_plot, *child_plots, child_idx],
             )
             
-    with gr.Tab('PlayGround (eig)', visible=True) as test_playground_tab2:
-        eigvecs = gr.State(np.array([]))
-        with gr.Row():
-            with gr.Column(scale=5, min_width=200):
-                gr.Markdown("### Step 1: Load Images")
-                input_gallery, submit_button, clear_images_button, dataset_dropdown, num_images_slider, random_seed_slider, load_images_button = make_input_images_section(n_example_images=100)
-                submit_button.visible = False
-                num_images_slider.value = 30
-                
-                false_placeholder = gr.Checkbox(label="False", value=False, elem_id="false_placeholder", visible=False)
-                no_prompt = gr.Textbox("", label="", elem_id="empty_placeholder", type="text", placeholder="", visible=False)
-                
-                
-            with gr.Column(scale=5, min_width=200):
-                gr.Markdown("### Step 2a: Run Backbone and NCUT")
-                with gr.Accordion(label="Backbone Parameters", visible=True, open=False):
-                    [
-                        model_dropdown, layer_slider, node_type_dropdown, num_eig_slider, 
-                        affinity_focal_gamma_slider, num_sample_ncut_slider, ncut_knn_slider, ncut_indirect_connection, ncut_make_orthogonal, 
-                        embedding_method_dropdown, embedding_metric_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
-                        perplexity_slider, n_neighbors_slider, min_dist_slider, 
-                        sampling_method_dropdown, ncut_metric_dropdown, positive_prompt, negative_prompt
-                    ] = make_parameters_section(ncut_parameter_dropdown=False, tsne_parameter_dropdown=False)
-                    num_eig_slider.value = 1024
-                    num_eig_slider.visible = False
-                submit_button = gr.Button("🔴 RUN NCUT", elem_id="run_ncut", variant='primary')
-                logging_text = gr.Textbox("Logging information", label="Logging", elem_id="logging", type="text", placeholder="Logging information", autofocus=False, autoscroll=False)
-                submit_button.click(
-                    partial(run_fn, n_ret=1, only_eigvecs=True),
-                    inputs=[
-                        input_gallery, model_dropdown, layer_slider, num_eig_slider, node_type_dropdown, 
-                        positive_prompt, negative_prompt,
-                        false_placeholder, no_prompt, no_prompt, no_prompt,
-                        affinity_focal_gamma_slider, num_sample_ncut_slider, ncut_knn_slider, ncut_indirect_connection, ncut_make_orthogonal, 
-                        embedding_method_dropdown, embedding_metric_dropdown, num_sample_tsne_slider, knn_tsne_slider, 
-                        perplexity_slider, n_neighbors_slider, min_dist_slider, sampling_method_dropdown, ncut_metric_dropdown
-                    ],
-                    outputs=[eigvecs, logging_text],
-                )
-                gr.Markdown("### Step 2b: Pick an Image")
-                from gradio_image_prompter import ImagePrompter
-                with gr.Row():
-                    image1_slider = gr.Slider(0, 100, step=1, label="Image#1 Index", value=0, elem_id="image1_slider", interactive=True)
-                load_one_image_button = gr.Button("🔴 Load Image", elem_id="load_one_image_button", variant='primary')
-                gr.Markdown("### Step 2c: Draw a Point")
-                gr.Markdown("""
-                    <h5>
-                    🖱️ Left Click: Foreground </br>
-                    </h5>
-                """)
-                prompt_image1 = ImagePrompter(show_label=False, elem_id="prompt_image1", interactive=False)
-                def update_prompt_image(original_images, index):
-                    images = original_images
-                    if images is None:
-                        return 
-                    total_len = len(images)
-                    if total_len == 0:
-                        return 
-                    if index >= total_len:
-                        index = total_len - 1
-                                            
-                    return ImagePrompter(value={'image': images[index][0], 'points': []}, interactive=True)
-                    # return gr.Image(value=images[index][0], elem_id=f"prompt_image{randint}", interactive=True)
-                load_one_image_button.click(update_prompt_image, inputs=[input_gallery, image1_slider], outputs=[prompt_image1])
-                
-            child_idx = gr.State([])
-            current_idx = gr.State(None)
-            n_eig = gr.State(64)
-            with gr.Column(scale=5, min_width=200):
-                gr.Markdown("### Step 3: Check groupping")
-                child_distance_slider = gr.Slider(0, 0.5, step=0.001, label="Child Distance", value=0.1, elem_id="child_distance_slider", interactive=True)
-                child_distance_slider.visible = False
-                overlay_image_checkbox = gr.Checkbox(label="Overlay Image", value=True, elem_id="overlay_image_checkbox", interactive=True)
-                n_eig_slider = gr.Slider(0, 1024, step=1, label="Number of Eigenvectors", value=256, elem_id="n_eig_slider", interactive=True)
-                run_button = gr.Button("🔴 RUN", elem_id="run_groupping", variant='primary')
-                with gr.Row():
-                    doublue_eigs_button = gr.Button("⬇️ +eigvecs", elem_id="doublue_eigs_button", variant='secondary')
-                    half_eigs_button = gr.Button("⬆️ -eigvecs", elem_id="half_eigs_button", variant='secondary')
-                current_plot = gr.Gallery(value=None, label="Current", show_label=True, elem_id="current_plot", interactive=False, rows=[1], columns=[2])
-    
-        def relative_xy(prompts):
-            image = prompts['image']
-            points = np.asarray(prompts['points'])
-            if points.shape[0] == 0:
-                return [], []
-            is_point = points[:, 5] == 4.0
-            points = points[is_point]
-            is_positive = points[:, 2] == 1.0
-            is_negative = points[:, 2] == 0.0
-            xy = points[:, :2].tolist()
-            if isinstance(image, str):
-                image = Image.open(image)
-                image = np.array(image)
-            h, w = image.shape[:2]
-            new_xy = [(x/w, y/h) for x, y in xy]
-            # print(new_xy)
-            return new_xy, is_positive
-        
-        def xy_eigvec(prompts, image_idx, eigvecs):
-            eigvec = eigvecs[image_idx]
-            xy, is_positive = relative_xy(prompts)
-            for i, (x, y) in enumerate(xy):
-                if not is_positive[i]:
-                    continue
-                x = int(x * eigvec.shape[1])
-                y = int(y * eigvec.shape[0])
-                return eigvec[y, x], (y, x)
-        
-        from ncut_pytorch.ncut_pytorch import _transform_heatmap
-        def _run_heatmap_fn(images, eigvecs, prompt_image_idx, prompt_points, n_eig, flat_idx=None, raw_heatmap=False, overlay_image=True):
-            left = eigvecs[..., :n_eig]
-            if flat_idx is not None:
-                right = eigvecs.reshape(-1, eigvecs.shape[-1])[flat_idx]
-                y, x = None, None
-            else:
-                right, (y, x) = xy_eigvec(prompt_points, prompt_image_idx, eigvecs)
-            right = right[:n_eig]
-            left = F.normalize(left, p=2, dim=-1)
-            _right = F.normalize(right, p=2, dim=-1)
-            heatmap = left @ _right.unsqueeze(-1)
-            heatmap = heatmap.squeeze(-1)
-            # heatmap = 1 - heatmap
-            # heatmap = _transform_heatmap(heatmap)
-            if raw_heatmap:
-                return heatmap
-            # apply hot colormap and covert to PIL image 256x256
-            # gr.Info(f"heatmap vmin: {heatmap.min()}, vmax: {heatmap.max()}, mean: {heatmap.mean()}")
-            heatmap = heatmap.cpu().numpy()
-            hot_map = matplotlib.colormaps['hot']
-            heatmap = hot_map(heatmap)
-            pil_images = to_pil_images(torch.tensor(heatmap), target_size=256, force_size=True)
-            if overlay_image:
-                overlaied_images = []
-                for i_image in range(len(images)):
-                    rgb_image = images[i_image].resize((256, 256))
-                    rgb_image = np.array(rgb_image)
-                    heatmap_image = np.array(pil_images[i_image])[..., :3]
-                    blend_image = 0.5 * rgb_image + 0.5 * heatmap_image
-                    blend_image = Image.fromarray(blend_image.astype(np.uint8))
-                    overlaied_images.append(blend_image)
-                pil_images = overlaied_images
-            return pil_images, (y, x)
-
-        @torch.no_grad()
-        def run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx=None, overlay_image=True):
-            gr.Info(f"current number of eigenvectors: {n_eig}", 2)
-            eigvecs = torch.tensor(eigvecs)
-            image1_slider = min(image1_slider, len(images)-1)
-            images = [image[0] for image in images]
-            if isinstance(images[0], str):
-                images = [Image.open(image[0]).convert("RGB").resize((256, 256)) for image in images]
-                        
-            current_heatmap, (y, x) = _run_heatmap_fn(images, eigvecs, image1_slider, prompt_image1, n_eig, flat_idx, overlay_image=overlay_image)
-            
-            return current_heatmap
-        
-        def doublue_eigs_wrapper(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx=None, overlay_image=True):
-            n_eig = int(n_eig*2)
-            n_eig = min(n_eig, eigvecs.shape[-1])
-            n_eig = max(n_eig, 1)
-            return gr.update(value=n_eig), run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, flat_idx, overlay_image=overlay_image)
-                
-        def half_eigs_wrapper(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, current_idx=None, overlay_image=True):
-            n_eig = int(n_eig/2)
-            n_eig = min(n_eig, eigvecs.shape[-1])
-            n_eig = max(n_eig, 1)
-            return gr.update(value=n_eig), run_heatmap(images, eigvecs, image1_slider, prompt_image1, n_eig, distance_slider, current_idx, overlay_image=overlay_image)
-                
-        none_placeholder = gr.State(None)
-        run_button.click(
-            run_heatmap,
-            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, none_placeholder, overlay_image_checkbox],
-            outputs=[current_plot],
-        )
-        
-        doublue_eigs_button.click(
-            doublue_eigs_wrapper,
-            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, none_placeholder, overlay_image_checkbox],
-            outputs=[n_eig_slider, current_plot],
-        )
-        
-        half_eigs_button.click(
-            half_eigs_wrapper,
-            inputs=[input_gallery, eigvecs, image1_slider, prompt_image1, n_eig_slider, child_distance_slider, current_idx, overlay_image_checkbox],
-            outputs=[n_eig_slider, current_plot],
-        )
         
     with gr.Tab('📄About'):
         with gr.Column():
@@ -4372,30 +4362,18 @@ with demo:
             label = "".join(label)
             return n_smiles, gr.update(label=label, value=False)
         
-        def unlock_tabs_with_info(n_smiles):
-            if n_smiles == unlock_value:
-                gr.Info("🔓 unlocked tabs", 2)
-                return gr.update(visible=True)
-            return gr.update()
 
-        def unlock_tabs(n_smiles):
+        def unlock_tabs(n_smiles, n_tab=1):
             if n_smiles == unlock_value:
-                return gr.update(visible=True)
-            return gr.update()
+                gr.Info("🔓 unlocked tabs", 2)
+                return [gr.update(visible=True)] * n_tab
+            return [gr.update()] * n_tab
         
         hidden_button.change(update_smile, [n_smiles], [n_smiles, hidden_button])
-        hidden_button.change(unlock_tabs_with_info, n_smiles, tab_alignedcut_advanced)
-        hidden_button.change(unlock_tabs, n_smiles, tab_model_aligned_advanced)
-        hidden_button.change(unlock_tabs, n_smiles, tab_recursivecut_advanced)
-        hidden_button.change(unlock_tabs, n_smiles, tab_compare_models_advanced)
-        hidden_button.change(unlock_tabs, n_smiles, tab_directed_ncut)
-        hidden_button.change(unlock_tabs, n_smiles, test_playground_tab)
+        hidden_tabs = [tab_alignedcut_advanced, tab_model_aligned_advanced, tab_recursivecut_advanced, 
+                        tab_compare_models_advanced, tab_directed_ncut, test_playground_tab, tab_aligned, tab_lisa]
+        hidden_button.change(partial(unlock_tabs, n_tab=len(hidden_tabs)), [n_smiles], hidden_tabs)
                 
-    # with gr.Row():
-        # with gr.Column():
-            # gr.Markdown("##### This demo is for `ncut-pytorch`, [Documentation](https://ncut-pytorch.readthedocs.io/) ")
-        # with gr.Column():
-            # gr.Markdown("###### Running out of GPU Quota? Try [Demo](https://ncut-pytorch.readthedocs.io/en/latest/demo/) hosted at UPenn")
     with gr.Row():
         gr.Markdown("**This demo is for Python package `ncut-pytorch`, [Documentation](https://ncut-pytorch.readthedocs.io/)**")