tried to change to dropdown

Home.py

@@ -21,8 +21,9 @@ st.write(intro_text)
 
 # 4 PAGES
 st.subheader('Pages')
-sections_text = """Overall, there are 4 features in this web app:
+sections_text = """Overall, there are x features in this web app:
 1) Disentanglement visualizer
+2) Concept vectors comparison and aggregation
 ...
 """
 st.write(sections_text)

pages/1_Disentanglement.py

@@ -20,18 +20,14 @@ SECONDARY_COLOR = '#bce7db'
 
 st.title('Disentanglement studies')
 st.write('> **What concepts can be disentangled in the latent spae of a model?**')
-st.write("""Explain more in depth""")
+st.write("""Explanation on the functionalities to come.""")
 
 instruction_text = """Instruction to input:
-1. Choosing image: Users can choose a specific image by entering **Image ID** and hit the _Choose the defined image_ button or can generate an image randomly by hitting the _Generate a random image_ button.
-2. Choosing epsilon: **Epsilon** is the amount of perturbation on the original image under attack. The higher the epsilon is, the more pertubed the image is, the more confusion made to the model. 
-Users can choose a specific epsilon by engtering **Epsilon** and hit the _Choose the defined epsilon_ button.
-Users can also let the algorithm find the smallest epsilon automatically by hitting the _Find the smallest epsilon automatically_ button.
-The underlying algorithm will iterate through a set of epsilon in ascending order until reaching the **maximum value of epsilon**.
-After each iteration, the epsilon will increase by an amount equal to **step** variable.
-Users can change the default values of the two variable value optionally.
+1. Choosing concept:
+2. Choosing image: Users can choose a specific image by entering **Image ID** and hit the _Choose the defined image_ button or can generate an image randomly by hitting the _Generate a random image_ button.
+3. Choosing epsilon: **Epsilon** is the lambda amount of translation along the disentangled concept axis. A negative epsilon changes the image in the direction of the concept, a positive one pushes the image away from the concept. 
 """
-st.write("To use the functionality below, users need to input the **image** and the **epsilon**.")
+st.write("To use the functionality below, users need to input the **concept** to disentangle, an **image** id and the **epsilon** of variation along the disentangled axis.")
 with st.expander("See more instruction", expanded=False):
     st.write(instruction_text)
 
@@ -42,6 +38,7 @@ with open(annotations_file, 'rb') as f:
 
 ann_df = pd.read_csv('./data/annotated_files/sim_seeds0000-10000.csv')
 concepts = './data/concepts.txt'
+
 with open(concepts) as f:
     labels = [line.strip() for line in f.readlines()]
 
@@ -62,16 +59,17 @@ with input_col_1:
         
         # image_id = st.number_input('Image ID: ', format='%d', step=1)
         st.write('**Choose a concept to disentangle**')
-        chosen_text_id_input = st.empty()
-        concept_id = chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
-        
+        # chosen_text_id_input = st.empty()
+        # concept_id = chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
+        concept_id = st.selectbox('Concept:', tuple(labels), value=st.session_state.concept_id)
+
         choose_text_button = st.form_submit_button('Choose the defined concept')
-        random_text = st.form_submit_button('Select a random concept')
+        # random_text = st.form_submit_button('Select a random concept')
 
-        if random_text:
-            concept_id = random.choice(labels)
-            st.session_state.concept_id = concept_id
-            chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
+        # if random_text:
+        #     concept_id = random.choice(labels)
+        #     st.session_state.concept_id = concept_id
+        #     chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
             
         if choose_text_button:
             concept_id = str(concept_id)
@@ -103,7 +101,7 @@ smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgr
 with output_col_1:
     separation_vector, number_important_features = get_separation_space(concept_id, annotations, ann_df)
     # st.write(f'Class ID {input_id} - {input_label}: {pred_prob*100:.3f}% confidence')
-    st.write('Separation vector', separation_vector)
+    st.write('Concept vector', separation_vector)
     header_col_1.write(f'Concept {concept_id} - Number of relevant nodes: {number_important_features}')
 
 # ----------------------------- INPUT column 2 & 3 ----------------------------        

pages/{2_todo.py → 2_Concepts_comparison.py}

@@ -6,21 +6,18 @@ import plotly.graph_objects as go
 
 import graphviz
 
-from backend.maximally_activating_patches import load_layer_infos, load_activation, get_receptive_field_coordinates
+#from backend.maximally_activating_patches import load_layer_infos, load_activation, get_receptive_field_coordinates
 from frontend import on_click_graph
-from backend.utils import load_dataset_dict
+#from backend.utils import load_dataset_dict
 
 HIGHTLIGHT_COLOR = '#e7bcc5'
 st.set_page_config(layout='wide')
 
 
-st.title('Maximally activating image patches')
-st.write('> **What patterns maximally activate this channel in ConvNeXt model?**')
-st.write("""The maximally activating image patches method is a technique used in visualizing the interpretation of convolutional neural networks. 
-It works by identifying the regions of the input image that activate a particular neuron in the convolutional layer, 
-thus revealing the features that the neuron is detecting. To achieve this, the method generates image patches then feeds into the model while monitoring the neuron's activation. 
-The algorithm then selects the patch that produces the highest activation and overlays it on the original image to visualize the features that the neuron is responding to.
-""")
+st.title('Comparison among concept vectors')
+st.write('> **How do the concept vectors relate to each other?**')
+st.write('> **What is their join impact on the image?**')
+st.write("""Description to write""")
 
 # -------------------------- LOAD DATASET ---------------------------------
 dataset_dict = load_dataset_dict()