cumulative change

backend/disentangle_concepts.py

@@ -103,6 +103,10 @@ def regenerate_images(model, z, decision_boundary, min_epsilon=-3, max_epsilon=3
 
     return images, lambdas
 
+def generate_joint_effect(model, z, decision_boundaries, min_epsilon=-3, max_epsilon=3, count=5, latent_space='Z'):
+    decision_boundary_joint = np.sum(decision_boundaries, axis=1)
+    return regenerate_images(model, z, decision_boundary_joint, min_epsilon=min_epsilon, max_epsilon=max_epsilon, count=count, latent_space=latent_space)
+    
 def generate_original_image(z, model, latent_space='Z'):
     """
     The generate_original_image function takes in a latent vector and the model,

pages/2_Concepts_comparison.py

@@ -5,8 +5,8 @@ import pickle
 import pandas as pd
 import numpy as np
 from pyvis.network import Network
-import networkx as nx
 
+import random
 from sklearn.metrics.pairwise import cosine_similarity
 
 from matplotlib.backends.backend_agg import RendererAgg
@@ -94,8 +94,6 @@ smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgr
 # ---------------------------- DISPLAY COL 1 ROW 1 ------------------------------
 with output_col_1:
     vectors, nodes_in_common, performances = get_concepts_vectors(concept_ids, annotations, ann_df, latent_space=space_id)
-    # st.write(f'Class ID {input_id} - {input_label}: {pred_prob*100:.3f}% confidence')
-    #st.write('Concept vector', separation_vector)
     header_col_1.write(f'Concepts {", ".join(concept_ids)} - Latent space {space_id} - Relevant nodes in common: {nodes_in_common} - Performance of the concept vectors: {performances}')# - Nodes {",".join(list(imp_nodes))}')
 
     edges = []
@@ -144,7 +142,7 @@ with output_col_1:
 
 with output_col_2:
     with open('data/CLIP_vecs.pkl', 'rb') as f:
-        vectors = pickle.load(f)
+        vectors_CLIP = pickle.load(f)
         
     # st.write(f'Class ID {input_id} - {input_label}: {pred_prob*100:.3f}% confidence')
     #st.write('Concept vector', separation_vector)
@@ -155,7 +153,7 @@ with output_col_2:
         for c2 in concept_ids:
             if c1 != c2:
                 print(f'Similarity between {c1} and {c2}')
-                similarity = cosine_similarity(vectors[c1].reshape(1, -1), vectors[c2].reshape(1, -1))
+                similarity = cosine_similarity(vectors_CLIP[c1].reshape(1, -1), vectors_CLIP[c2].reshape(1, -1))
                 print(np.round(similarity[0][0], 3))
                 edges_clip.append((c1, c2, float(np.round(similarity[0][0], 3))))
 
@@ -195,65 +193,69 @@ with output_col_2:
     components.html(HtmlFile.read(), height=435)
     
 # ----------------------------- INPUT column 2 & 3 ----------------------------        
-# with input_col_2:
-#    with st.form('image_form'):
+with input_col_2:
+   with st.form('image_form'):
         
-#         # image_id = st.number_input('Image ID: ', format='%d', step=1)
-#         st.write('**Choose or generate a random image to test the disentanglement**')
-#         chosen_image_id_input = st.empty()
-#         image_id = chosen_image_id_input.number_input('Image ID:', format='%d', step=1, value=st.session_state.image_id)
+        # image_id = st.number_input('Image ID: ', format='%d', step=1)
+        st.write('**Choose or generate a random image to test the disentanglement**')
+        chosen_image_id_input = st.empty()
+        image_id = chosen_image_id_input.number_input('Image ID:', format='%d', step=1, value=st.session_state.image_id)
         
-#         choose_image_button = st.form_submit_button('Choose the defined image')
-#         random_id = st.form_submit_button('Generate a random image')
+        choose_image_button = st.form_submit_button('Choose the defined image')
+        random_id = st.form_submit_button('Generate a random image')
 
-#         if random_id:
-#             image_id = random.randint(0, 100000)
-#             st.session_state.image_id = image_id
-#             chosen_image_id_input.number_input('Image ID:', format='%d', step=1, value=st.session_state.image_id)
+        if random_id:
+            image_id = random.randint(0, 50000)
+            st.session_state.image_id = image_id
+            chosen_image_id_input.number_input('Image ID:', format='%d', step=1, value=st.session_state.image_id)
             
-#         if choose_image_button:
-#             image_id = int(image_id)
-#             st.session_state.image_id = int(image_id)
-#         # st.write(image_id, st.session_state.image_id)
-
-# with input_col_3:
-#     with st.form('Variate along the disentangled concept'):
-#         st.write('**Set range of change**')
-#         chosen_epsilon_input = st.empty()
-#         epsilon = chosen_epsilon_input.number_input('Epsilon:', min_value=1, step=1)
-#         epsilon_button = st.form_submit_button('Choose the defined epsilon')
+        if choose_image_button:
+            image_id = int(image_id)
+            st.session_state.image_id = int(image_id)
+        # st.write(image_id, st.session_state.image_id)
+
+with input_col_3:
+    with st.form('Variate along the disentangled concepts'):
+        st.write('**Set range of change**')
+        chosen_epsilon_input = st.empty()
+        epsilon = chosen_epsilon_input.number_input('Epsilon:', min_value=1, step=1)
+        epsilon_button = st.form_submit_button('Choose the defined epsilon')
 
 # # ---------------------------- DISPLAY COL 2 ROW 1 ------------------------------
 
-# #model = torch.load('./data/model_files/pytorch_model.bin', map_location=torch.device('cpu'))
-# with dnnlib.util.open_url('./data/model_files/network-snapshot-010600.pkl') as f:
-#     model = legacy.load_network_pkl(f)['G_ema'].to('cpu') # type: ignore
 
-# original_image_vec = annotations['z_vectors'][st.session_state.image_id]
-# img = generate_original_image(original_image_vec, model)
-# # input_image = original_image_dict['image']
-# # input_label = original_image_dict['label']
-# # input_id = original_image_dict['id']
+with dnnlib.util.open_url('./data/model_files/network-snapshot-010600.pkl') as f:
+    model = legacy.load_network_pkl(f)['G_ema'].to('cpu') # type: ignore
+
+if st.session_state.space_id == 'Z':
+    original_image_vec = annotations['z_vectors'][st.session_state.image_id]
+else:
+    original_image_vec = annotations['w_vectors'][st.session_state.image_id]
+
+img = generate_original_image(original_image_vec, model, latent_space=st.session_state.space_id)
+# input_image = original_image_dict['image']
+# input_label = original_image_dict['label']
+# input_id = original_image_dict['id']
 
-# with smoothgrad_col_3:
-#     st.image(img)
-#     smooth_head_3.write(f'Base image')
+with smoothgrad_col_3:
+    st.image(img)
+    smooth_head_3.write(f'Base image')
 
 
-# images, lambdas = regenerate_images(model, original_image_vec, separation_vector, min_epsilon=-(int(epsilon)), max_epsilon=int(epsilon))
+images, lambdas = generate_joint_effect(model, original_image_vec, vectors, min_epsilon=-(int(epsilon)), max_epsilon=int(epsilon), latent_space=st.session_state.space_id)
 
-# with smoothgrad_col_1:
-#     st.image(images[0])
-#     smooth_head_1.write(f'Change of {np.round(lambdas[0], 2)}')
+with smoothgrad_col_1:
+    st.image(images[0])
+    smooth_head_1.write(f'Change of {np.round(lambdas[0], 2)}')
 
-# with smoothgrad_col_2:
-#     st.image(images[1])
-#     smooth_head_2.write(f'Change of {np.round(lambdas[1], 2)}')
+with smoothgrad_col_2:
+    st.image(images[1])
+    smooth_head_2.write(f'Change of {np.round(lambdas[1], 2)}')
 
-# with smoothgrad_col_4:
-#     st.image(images[3])
-#     smooth_head_4.write(f'Change of {np.round(lambdas[3], 2)}')
+with smoothgrad_col_4:
+    st.image(images[3])
+    smooth_head_4.write(f'Change of {np.round(lambdas[3], 2)}')
 
-# with smoothgrad_col_5:
-#     st.image(images[4])
-#     smooth_head_5.write(f'Change of {np.round(lambdas[4], 2)}')
+with smoothgrad_col_5:
+    st.image(images[4])
+    smooth_head_5.write(f'Change of {np.round(lambdas[4], 2)}')