updating wb to textiles

data/CLIP_vecs_vases.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6299cd65f0635d6077788b135520ee8e88063930c63db458e643d77cba7b6ee
-size 995715

data/annotated_files/seeds0000-100000.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b3a4fd155fa86df0953ad1cb660d50729189606de307fcee09fd893ba047228
-size 420351795

data/annotated_files/seeds0000-50000.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd1bd97b8ff508b1d4a7ef43323530368ace65b35d12d84a914913f541187298
-size 314939226

data/annotated_files/sim_seeds0000-100000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e0b08d729f87f827d3d88327b33ff22d8413cb7aa7057c0c4ccd384d72a2c21
-size 21090135

data/annotated_files/sim_seeds0000-50000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da82633e4296ae78ce9e3e208fae374ae8983137566101060aadd11ffd3b0ff7
-size 50535430

data/model_files/network-snapshot-010600.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a46e8aecd50191b82632b5de7bf3b9e219a59564c54994dd203f016b7a8270e
-size 357344749

data/old/ImageNet_metadata.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e53b0fc17cd5c8811ca08b7ff908cd2bbd625147686ef8bc020cb85a5a4546e5
-size 3027633

data/old/activation/convnext_activation.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0354b28bcca4e3673888124740e3d82882cbf38af8cd3007f48a7a5db983f487
-size 33350177

data/old/activation/mobilenet_activation.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5abc76e9318fadee18f35bb54e90201bf28699cf75140b5d2482d42243fad302
-size 13564581

data/old/activation/resnet_activation.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:668bea355a5504d74f79d20d02954040ad572f50455361d7d17125c7c8b1561c
-size 23362905

data/old/dot_architectures/convnext_architecture.dot

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:41a258a40a93615638ae504770c14e44836c934badbe48f18148f5a750514ac9
-size 9108

data/old/layer_infos/convnext_layer_infos.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e82ea48865493107b97f37da58e370f0eead5677bf10f25f237f10970aedb6f
-size 1678

data/old/layer_infos/mobilenet_layer_infos.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a11df5f0b23040d11ce817658a989c8faf19faa06a8cbad727b635bac824e917
-size 3578

data/old/layer_infos/resnet_layer_infos.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21e1787382f1e1c206b81d2c4fe207fb6d41f4cf186d5afc32fc056dd21e10d6
-size 5155

data/old/preprocessed_image_net/val_data_0.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2698bdc240555e2a46a40936df87275bc5852142d30e921ae0dad9289b0f576f
-size 906108480

data/old/preprocessed_image_net/val_data_1.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21780d77e212695dbee84d6d2ad17a5a520bc1634f68e1c8fd120f069ad76da1
-size 907109023

data/old/preprocessed_image_net/val_data_2.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2cfc83b78420baa1b2c3a8da92e7fba1f33443d506f483ecff13cdba2035ab3c
-size 907435149

data/old/preprocessed_image_net/val_data_3.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f5e2c7cb4d6bae17fbd062a0b46f2cee457ad466b725f7bdf0f8426069cafee
-size 906089333

data/old/preprocessed_image_net/val_data_4.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ed53c87ec8b9945db31f910eb44b7e3092324643de25ea53a99fc29137df854
-size 905439763

data/{CLIP_vecs.pkl → stored_vectors/scores_colors_hsv.csv}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2971a01a74a391c752fff9ba91c2939ffc6b29165842a87b911e67d9658df53
-size 412234
+oid sha256:93f5789a80465ca7b21713819bc444d72239fa1b7ae56adf69e3323e0f3bedd1
+size 974247

data/vase_annotated_files/seeds0000-20000.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e790910bf45c0d5a84e74c9011b88012f59d0fc27b19987c890b891c57ab739c
-size 125913423

data/vase_annotated_files/sim_Fabric_seeds0000-20000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20fa48320e20998aad5665610083843705608a5f06ff081e4395ee4b5ac9cba3
-size 9731011

data/vase_annotated_files/sim_Provenance_seeds0000-20000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a421ffd119eee312249c9fbd05ac65460849e71f538d05fad223cb55423f315f
-size 18066428

data/vase_annotated_files/sim_Shape Name_seeds0000-20000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e258361e0db7c208ae67654c08ed5b900df10980e82e84bcddd3de89428f679a
-size 30853761

data/vase_annotated_files/sim_Technique_seeds0000-20000.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e3d3425e15d76d47a8829783cadbd7072698083df199617a8423d5ccb9d88714
-size 2484876

data/vase_model_files/network-snapshot-003800.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:42be0a24e7021dc66a9353c3a904494bb8e64b62e00e535ad3b03ad18238b0d2
-size 357349976

pages/1_Omniart_Disentanglement.py

@@ -1,202 +0,0 @@
-import streamlit as st
-import pickle
-import pandas as pd
-import numpy as np
-import random
-import torch
-
-from matplotlib.backends.backend_agg import RendererAgg
-
-from backend.disentangle_concepts import *
-import torch_utils
-import dnnlib
-import legacy
-
-_lock = RendererAgg.lock
-
-
-st.set_page_config(layout='wide')
-BACKGROUND_COLOR = '#bcd0e7'
-SECONDARY_COLOR = '#bce7db'
-
-
-st.title('Disentanglement studies')
-st.write('> **What concepts can be disentangled in the latent spae of a model?**')
-st.write("""Explanation on the functionalities to come.""")
-
-instruction_text = """Instruction to input:
-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 **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)
-
-    
-annotations_file = './data/annotated_files/seeds0000-50000.pkl'
-with open(annotations_file, 'rb') as f:
-    annotations = pickle.load(f)
-
-ann_df = pd.read_csv('./data/annotated_files/sim_seeds0000-50000.csv')
-concepts = './data/concepts.txt'
-
-with open(concepts) as f:
-    labels = [line.strip() for line in f.readlines()]
-
-if 'image_id' not in st.session_state:
-    st.session_state.image_id = 0
-if 'projection' not in st.session_state:
-    st.session_state.projection = False
-if 'concept_id' not in st.session_state:
-    st.session_state.concept_id = 'Abstract'
-if 'space_id' not in st.session_state:
-    st.session_state.space_id = 'Z'
-
-# def on_change_random_input():
-#     st.session_state.image_id = st.session_state.image_id
-
-# ----------------------------- INPUT ----------------------------------
-st.header('Input')
-input_col_1, input_col_2, input_col_3 = st.columns(3)
-# --------------------------- INPUT column 1 ---------------------------
-with input_col_1:
-    with st.form('text_form'):
-        
-        # 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)
-        concept_id = st.selectbox('Concept:', tuple(labels))
-
-        st.write('**Choose a latent space to disentangle**')
-        # chosen_text_id_input = st.empty()
-        # concept_id = chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
-        space_id = st.selectbox('Space:', tuple(['Z', 'W']))
-
-        choose_text_button = st.form_submit_button('Choose the defined concept and space to disentangle')
-        # 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 choose_text_button:
-            concept_id = str(concept_id)
-            st.session_state.concept_id = concept_id
-            space_id = str(space_id)
-            st.session_state.space_id = space_id
-        # st.write(image_id, st.session_state.image_id)
-
-# ---------------------------- SET UP OUTPUT ------------------------------
-epsilon_container = st.empty()
-st.header('Output')
-st.subheader('Concept vector')
-
-# perform attack container
-# header_col_1, header_col_2, header_col_3, header_col_4, header_col_5 = st.columns([1,1,1,1,1])
-# output_col_1, output_col_2, output_col_3, output_col_4, output_col_5 = st.columns([1,1,1,1,1])
-header_col_1, header_col_2 = st.columns([5,1])
-output_col_1, output_col_2 = st.columns([5,1])
-
-st.subheader('Derivations along the concept vector')
-
-# prediction error container
-error_container = st.empty()
-smoothgrad_header_container = st.empty()
-
-# smoothgrad container
-smooth_head_1, smooth_head_2, smooth_head_3, smooth_head_4, smooth_head_5 = st.columns([1,1,1,1,1])
-smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgrad_col_5 = st.columns([1,1,1,1,1])
-
-# ---------------------------- DISPLAY COL 1 ROW 1 ------------------------------
-with output_col_1:
-    separation_vector, number_important_features, imp_nodes, performance = get_separation_space(concept_id, annotations, ann_df, latent_space=st.session_state.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'Concept {concept_id} - Space {st.session_state.space_id} - Number of relevant nodes: {number_important_features} - Val classification performance: {performance}')# - Nodes {",".join(list(imp_nodes))}')
-
-# ----------------------------- INPUT column 2 & 3 ----------------------------        
-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)
-        
-        choose_image_button = st.form_submit_button('Choose the defined image')
-        random_id = st.form_submit_button('Generate a random image')
-        projection_id = st.form_submit_button('Generate an image on the boudary')
-
-        if random_id or projection_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)
-            st.session_state.projection = False
-            
-            if projection_id:
-                st.session_state.projection = True
-            
-        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('Lambda:', min_value=1, step=1)
-        epsilon_button = st.form_submit_button('Choose the defined lambda')
-        st.write('**Select hierarchical levels to manipulate**')
-        layers = st.multiselect('Layers:', tuple(range(14)))
-        if len(layers) == 0:
-            layers = None
-        print(layers)
-        layers_button = st.form_submit_button('Choose the defined layers')
-        
-
-# ---------------------------- 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
-
-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]
-
-if st.session_state.projection:
-    original_image_vec = original_image_vec - np.dot(original_image_vec, separation_vector.T) * separation_vector
-    print(original_image_vec.shape)
-
-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')
-
-
-images, lambdas = regenerate_images(model, original_image_vec, separation_vector, min_epsilon=-(int(epsilon)), max_epsilon=int(epsilon), latent_space=st.session_state.space_id, layers=layers)
-
-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_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)}')

pages/{5_Textiles_Disentanglement.py → 1_Textiles_Disentanglement.py}

@@ -23,18 +23,18 @@ SECONDARY_COLOR = '#bce7db'
 st.title('Disentanglement studies on the Textile Dataset')
 st.markdown(
     """
-    This is a demo of the Disentanglement studies on the [Oxford Vases Dataset](https://www.robots.ox.ac.uk/~vgg/data/oxbuildings/).
+    This is a demo of the Disentanglement studies on the [iMET Textiles Dataset](https://www.metmuseum.org/art/collection/search/85531).
     """,
     unsafe_allow_html=False,)
     
-annotations_file = './data/vase_annotated_files/seeds0000-20000.pkl'
+annotations_file = './data/textile_annotated_files/seeds0000-100000_S.pkl'
 with open(annotations_file, 'rb') as f:
     annotations = pickle.load(f)
 
-
+COLORS_LIST = []
 if 'image_id' not in st.session_state:
     st.session_state.image_id = 0
-if 'concept_ids' not in st.session_state:
+if 'color_ids' not in st.session_state:
     st.session_state.concept_ids =['AMPHORA']
 if 'space_id' not in st.session_state:
     st.session_state.space_id = 'W'

pages/3_Oxford_Vases_Disentanglement.py

@@ -1,178 +0,0 @@
-import streamlit as st
-import pickle
-import pandas as pd
-import numpy as np
-import random
-import torch
-
-from matplotlib.backends.backend_agg import RendererAgg
-
-from backend.disentangle_concepts import *
-import torch_utils
-import dnnlib
-import legacy
-
-_lock = RendererAgg.lock
-
-
-st.set_page_config(layout='wide')
-BACKGROUND_COLOR = '#bcd0e7'
-SECONDARY_COLOR = '#bce7db'
-
-
-st.title('Disentanglement studies on the Oxford Vases Dataset')
-st.markdown(
-    """
-    This is a demo of the Disentanglement studies on the [Oxford Vases Dataset](https://www.robots.ox.ac.uk/~vgg/data/oxbuildings/).
-    """,
-    unsafe_allow_html=False,)
-    
-annotations_file = './data/vase_annotated_files/seeds0000-20000.pkl'
-with open(annotations_file, 'rb') as f:
-    annotations = pickle.load(f)
-
-
-if 'image_id' not in st.session_state:
-    st.session_state.image_id = 0
-if 'concept_ids' not in st.session_state:
-    st.session_state.concept_ids =['AMPHORA']
-if 'space_id' not in st.session_state:
-    st.session_state.space_id = 'W'
-
-# def on_change_random_input():
-#     st.session_state.image_id = st.session_state.image_id
-
-# ----------------------------- INPUT ----------------------------------
-st.header('Input')
-input_col_1, input_col_2, input_col_3 = st.columns(3)
-# --------------------------- INPUT column 1 ---------------------------
-with input_col_1:
-    with st.form('text_form'):
-        
-        # image_id = st.number_input('Image ID: ', format='%d', step=1)
-        st.write('**Choose two options to disentangle**')
-        type_col = st.selectbox('Concept category:', tuple(['Provenance', 'Shape Name', 'Fabric', 'Technique']))
-        
-        ann_df = pd.read_csv(f'./data/vase_annotated_files/sim_{type_col}_seeds0000-20000.csv')
-        labels = list(ann_df.columns)
-        labels.remove('ID')
-        labels.remove('Unnamed: 0')
-        
-        concept_ids = st.multiselect('Concepts:', tuple(labels), max_selections=2, default=[labels[2], labels[3]])
-
-        st.write('**Choose a latent space to disentangle**')
-        space_id = st.selectbox('Space:', tuple(['W', 'Z']))
-
-        choose_text_button = st.form_submit_button('Choose the defined concept and space to disentangle')
-          
-        if choose_text_button:
-            concept_ids = list(concept_ids)
-            st.session_state.concept_ids = concept_ids
-            space_id = str(space_id)
-            st.session_state.space_id = space_id
-        # st.write(image_id, st.session_state.image_id)
-
-# ---------------------------- SET UP OUTPUT ------------------------------
-epsilon_container = st.empty()
-st.header('Output')
-st.subheader('Concept vector')
-
-# perform attack container
-# header_col_1, header_col_2, header_col_3, header_col_4, header_col_5 = st.columns([1,1,1,1,1])
-# output_col_1, output_col_2, output_col_3, output_col_4, output_col_5 = st.columns([1,1,1,1,1])
-header_col_1, header_col_2 = st.columns([5,1])
-output_col_1, output_col_2 = st.columns([5,1])
-
-st.subheader('Derivations along the concept vector')
-
-# prediction error container
-error_container = st.empty()
-smoothgrad_header_container = st.empty()
-
-# smoothgrad container
-smooth_head_1, smooth_head_2, smooth_head_3, smooth_head_4, smooth_head_5 = st.columns([1,1,1,1,1])
-smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgrad_col_5 = st.columns([1,1,1,1,1])
-
-# ---------------------------- DISPLAY COL 1 ROW 1 ------------------------------
-with output_col_1:
-    separation_vector, number_important_features, imp_nodes, performance = get_separation_space(concept_ids, annotations, ann_df, latent_space=st.session_state.space_id, samples=150)
-    # 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'Concept {st.session_state.concept_ids} - Space {st.session_state.space_id} - Number of relevant nodes: {number_important_features} - Val classification performance: {performance}')# - Nodes {",".join(list(imp_nodes))}')
-
-# ----------------------------- INPUT column 2 & 3 ----------------------------        
-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)
-        
-        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, 20000)
-            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('Lambda:', min_value=1, step=1)
-        epsilon_button = st.form_submit_button('Choose the defined lambda')
-        st.write('**Select hierarchical levels to manipulate**')
-        layers = st.multiselect('Layers:', tuple(range(14)))
-        if len(layers) == 0:
-            layers = None
-        print(layers)
-        layers_button = st.form_submit_button('Choose the defined layers')
-        
-
-# ---------------------------- 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/vase_model_files/network-snapshot-003800.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)
-
-top_pred = ann_df.loc[st.session_state.image_id, labels].astype(float).idxmax()
-# 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, predicted as {top_pred}')
-
-
-images, lambdas = regenerate_images(model, original_image_vec, separation_vector, min_epsilon=-(int(epsilon)), max_epsilon=int(epsilon), latent_space=st.session_state.space_id, layers=layers)
-
-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_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)}')

pages/4_Vase_Qualities_Comparison copy.py

@@ -1,268 +0,0 @@
-import streamlit as st
-import streamlit.components.v1 as components
-
-import dnnlib
-import legacy
-
-import pickle
-import pandas as pd
-import numpy as np
-from pyvis.network import Network
-
-import random
-from sklearn.metrics.pairwise import cosine_similarity
-
-from matplotlib.backends.backend_agg import RendererAgg
-
-from backend.disentangle_concepts import *
-
-_lock = RendererAgg.lock
-
-HIGHTLIGHT_COLOR = '#e7bcc5'
-st.set_page_config(layout='wide')
-
-
-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""")
-
-    
-annotations_file = './data/vase_annotated_files/seeds0000-20000.pkl'
-with open(annotations_file, 'rb') as f:
-    annotations = pickle.load(f)
-
-if 'image_id' not in st.session_state:
-    st.session_state.image_id = 0
-if 'concept_ids' not in st.session_state:
-    st.session_state.concept_ids = ['Provenance ADRIA']
-if 'space_id' not in st.session_state:
-    st.session_state.space_id = 'Z'
-if 'type_col' not in st.session_state:
-    st.session_state.type_col = 'Provenance'
-
-# def on_change_random_input():
-#     st.session_state.image_id = st.session_state.image_id
-
-# ----------------------------- INPUT ----------------------------------
-st.header('Input')
-input_col_1, input_col_2, input_col_3 = st.columns(3)
-# --------------------------- INPUT column 1 ---------------------------
-with input_col_1:
-    with st.form('text_form'):
-        
-        # image_id = st.number_input('Image ID: ', format='%d', step=1)
-        st.write('**Choose two options to disentangle**')
-        type_col = st.selectbox('Concept category:', tuple(['Provenance', 'Shape Name', 'Fabric', 'Technique']))
-        
-        ann_df = pd.read_csv(f'./data/vase_annotated_files/sim_{type_col}_seeds0000-20000.csv')
-        labels = list(ann_df.columns)
-        labels.remove('ID')
-        labels.remove('Unnamed: 0')
-        
-        concept_ids = st.multiselect('Concepts:', tuple(labels), default=[labels[2], labels[3]])
-
-        st.write('**Choose a latent space to disentangle**')
-        # chosen_text_id_input = st.empty()
-        # concept_id = chosen_text_id_input.text_input('Concept:', value=st.session_state.concept_id)
-        space_id = st.selectbox('Space:', tuple(['Z', 'W']))
-
-        choose_text_button = st.form_submit_button('Choose the defined concept and space to disentangle')
-        
-        if choose_text_button:
-            st.session_state.concept_ids = list(concept_ids)
-            space_id = str(space_id)
-            st.session_state.space_id = space_id
-            st.session_state.type_col = type_col
-        # st.write(image_id, st.session_state.image_id)
-
-# ---------------------------- SET UP OUTPUT ------------------------------
-epsilon_container = st.empty()
-st.header('Output')
-st.subheader('Concept vector')
-
-# perform attack container
-# header_col_1, header_col_2, header_col_3, header_col_4, header_col_5 = st.columns([1,1,1,1,1])
-# output_col_1, output_col_2, output_col_3, output_col_4, output_col_5 = st.columns([1,1,1,1,1])
-header_col_1, header_col_2 = st.columns([1,1])
-output_col_1, output_col_2 = st.columns([1,1])
-
-st.subheader('Derivations along the concept vector')
-
-# prediction error container
-error_container = st.empty()
-smoothgrad_header_container = st.empty()
-
-# smoothgrad container
-smooth_head_1, smooth_head_2, smooth_head_3, smooth_head_4, smooth_head_5 = st.columns([1,1,1,1,1])
-smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgrad_col_5 = st.columns([1,1,1,1,1])
-
-# ---------------------------- 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)
-    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 = []
-    for i in range(len(concept_ids)):
-        for j in range(len(concept_ids)):
-            if i != j:
-                print(f'Similarity between {concept_ids[i]} and {concept_ids[j]}')
-                similarity = cosine_similarity(vectors[i,:].reshape(1, -1), vectors[j,:].reshape(1, -1))
-                print(np.round(similarity[0][0], 3))
-                edges.append((concept_ids[i], concept_ids[j], np.round(similarity[0][0], 3)))
-
-    
-    net = Network(height="750px", width="100%",)
-    for e in edges:
-        src = e[0]
-        dst = e[1]
-        w = e[2]
-
-        net.add_node(src, src, title=src)
-        net.add_node(dst, dst, title=dst)
-        net.add_edge(src, dst, value=w, title=src + ' to ' + dst + ' similarity ' +str(w))
-    
-    # Generate network with specific layout settings
-    net.repulsion(
-                        node_distance=420,
-                        central_gravity=0.33,
-                        spring_length=110,
-                        spring_strength=0.10,
-                        damping=0.95
-                       )
-
-    # Save and read graph as HTML file (on Streamlit Sharing)
-    try:
-        path = '/tmp'
-        net.save_graph(f'{path}/pyvis_graph.html')
-        HtmlFile = open(f'{path}/pyvis_graph.html', 'r', encoding='utf-8')
-
-    # Save and read graph as HTML file (locally)
-    except:
-        path = '/html_files'
-        net.save_graph(f'{path}/pyvis_graph.html')
-        HtmlFile = open(f'{path}/pyvis_graph.html', 'r', encoding='utf-8')
-
-    # Load HTML file in HTML component for display on Streamlit page
-    components.html(HtmlFile.read(), height=435)
-
-with output_col_2:
-    with open('data/CLIP_vecs_vases.pkl', 'rb') as 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)
-    header_col_2.write(f'Concepts {", ".join(concept_ids)} - Latent space CLIP')# - Nodes {",".join(list(imp_nodes))}')
-
-    edges_clip = []
-    for c1 in concept_ids:
-        for c2 in concept_ids:
-            if c1 != c2:
-                
-                print(f'Similarity between {c1} and {c2}')
-                similarity = cosine_similarity(vectors_CLIP[st.session_state.type_col + ' ' + c1].reshape(1, -1), vectors_CLIP[st.session_state.type_col + ' ' + c2].reshape(1, -1))
-                print(np.round(similarity[0][0], 3))
-                edges_clip.append((c1, c2, np.round(float(np.round(similarity[0][0], 3)), 3)))
-
-
-    net_clip = Network(height="750px", width="100%",)
-    for e in edges_clip:
-        src = e[0]
-        dst = e[1]
-        w = e[2]
-
-        net_clip.add_node(src, src, title=src)
-        net_clip.add_node(dst, dst, title=dst)
-        net_clip.add_edge(src, dst, value=w, title=src + ' to ' + dst + ' similarity ' +str(w))
-    
-    # Generate network with specific layout settings
-    net_clip.repulsion(
-                        node_distance=420,
-                        central_gravity=0.33,
-                        spring_length=110,
-                        spring_strength=0.10,
-                        damping=0.95
-                       )
-
-    # Save and read graph as HTML file (on Streamlit Sharing)
-    try:
-        path = '/tmp'
-        net_clip.save_graph(f'{path}/pyvis_graph_clip.html')
-        HtmlFile = open(f'{path}/pyvis_graph_clip.html', 'r', encoding='utf-8')
-
-    # Save and read graph as HTML file (locally)
-    except:
-        path = '/html_files'
-        net_clip.save_graph(f'{path}/pyvis_graph_clip.html')
-        HtmlFile = open(f'{path}/pyvis_graph_clip.html', 'r', encoding='utf-8')
-
-    # Load HTML file in HTML component for display on Streamlit page
-    components.html(HtmlFile.read(), height=435)
-    
-# ----------------------------- INPUT column 2 & 3 ----------------------------        
-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)
-        
-        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, 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 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 ------------------------------
-
-
-with dnnlib.util.open_url('./data/vase_model_files/network-snapshot-003800.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')
-
-
-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_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_5:
-    st.image(images[4])
-    smooth_head_5.write(f'Change of {np.round(lambdas[4], 2)}')