added changed images

backend/disentangle_concepts.py

@@ -15,10 +15,10 @@ def get_separation_space(type_bin, annotations, df):
     svc = SVC(gamma='auto', kernel='linear')
     svc.fit(x_train, y_train)
     print(svc.score(x_val, y_val))
-    imp_features = (np.abs(svc.coef_) > 0.01).sum()
+    imp_features = (np.abs(svc.coef_) > 0.1).sum()
     return svc.coef_, imp_features
 
-def regenerate_images(model, z, decision_boundary, min_epsilon=-3, max_epsilon=3, count=11):
+def regenerate_images(model, z, decision_boundary, min_epsilon=-3, max_epsilon=3, count=5):
     device = torch.device('cpu')
     G = model.to(device) # type: ignore
 
@@ -28,7 +28,7 @@ def regenerate_images(model, z, decision_boundary, min_epsilon=-3, max_epsilon=3
     z = torch.from_numpy(z.copy()).to(device)
     decision_boundary = torch.from_numpy(decision_boundary.copy()).to(device)
         
-    lambdas = np.linspace(-3, 3, 11)
+    lambdas = np.linspace(min_epsilon, max_epsilon, count)
     images = []
     # Generate images.
     for _, lambda_ in enumerate(lambdas):
@@ -44,7 +44,8 @@ def regenerate_images(model, z, decision_boundary, min_epsilon=-3, max_epsilon=3
         img = G(z_0, label, truncation_psi=0.7, noise_mode='random')
         img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
         images.append(PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB'))
-    return images
+
+    return images, lambdas
 
 def generate_original_image(z, model):
     device = torch.device('cpu')

pages/1_Disentanglement.py

@@ -84,8 +84,10 @@ 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, 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 = st.columns([1])
+output_col_1 = st.columns([1])
 
 # prediction error container
 error_container = st.empty()
@@ -115,7 +117,7 @@ with input_col_2:
         random_id = st.form_submit_button('Generate a random image')
 
         if random_id:
-            image_id = random.randint(0, 50000)
+            image_id = random.randint(0, 10000)
             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)
             
@@ -128,7 +130,7 @@ 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, format='%.1f')
+        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 ------------------------------
@@ -142,83 +144,23 @@ img = generate_original_image(original_image_vec, model)
 
 with smoothgrad_col_3:
     st.image(img)
-    header_col_1.write(f'Base image')
+    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))
 
-# if pred_class_id == (input_id-1) and (epsilon_button or find_epsilon or setting_button):
-#     with output_col_3:
-#         if epsilon_button:
-#             perturbed_data, new_prob, new_id, new_label = perform_attack(input_image, input_id-1, epsilon)
-#         else:
-#             epsilons = [i*step_epsilon for i in range(1, 1001) if i*step_epsilon <= max_epsilon]
-#             with epsilon_container.container():
-#                 epsilon_container_text = 'Checking epsilon'
-#                 st.write(epsilon_container_text)
-#                 st.progress(0)
-        
-#             for i, e in enumerate(epsilons):
-                
-#                 perturbed_data, new_prob, new_id, new_label = perform_attack(input_image, input_id-1, e)
-#                 with epsilon_container.container():
-#                     epsilon_container_text = f'Checking epsilon={e:.3f}. Confidence={new_prob*100:.1f}%'
-#                     st.write(epsilon_container_text)
-#                     st.progress(i/len(epsilons))
-                
-#                 epsilon = e
-
-#                 if new_id != input_id - 1:
-#                     epsilon_container.empty()
-#                     st.balloons()
-#                     break
-#                 if i == len(epsilons)-1:
-#                     epsilon_container.error(f'FGSM failed to attack on this image at epsilon={e:.3f}. Set higher maximum value of epsilon or choose another image',
-#                                             icon = "🚫")
-
-#         perturbed_image = deprocess_image(perturbed_data.detach().numpy())[0].astype(np.uint8).transpose(1,2,0)
-#         perturbed_amount = perturbed_image - input_image
-#         header_col_3.write(f'Pertubed amount - epsilon={epsilon:.3f}')
-#         st.image(ShowImage(perturbed_amount))
-    
-#     with output_col_2:
-#         # st.write('plus sign')
-#         st.image(LoadImage('frontend/images/plus-sign.png'))
-    
-#     with output_col_4:
-#         # st.write('equal sign')
-#         st.image(LoadImage('frontend/images/equal-sign.png'))
-
-#     # ---------------------------- DISPLAY COL 5 ROW 1 ------------------------------
-#     with output_col_5:
-#         # st.write(f'ID {new_id+1} - {new_label}: {new_prob*100:.3f}% confidence')
-#         st.image(ShowImage(perturbed_image))
-#     header_col_5.write(f'Class ID {new_id+1} - {new_label}: {new_prob*100:.1f}% confidence')
-
-#     # -------------------------- DISPLAY SMOOTHGRAD ---------------------------
-#     smoothgrad_header_container.subheader('SmoothGrad visualization')
-
-#     with smoothgrad_col_1:
-#         smooth_head_1.write(f'SmoothGrad before attacked')
-#         heatmap_image, masked_image, mask = generate_images(st.session_state.image_id, epsilon=0)
-#         st.image(heatmap_image)
-#         st.image(masked_image) 
-#     with smoothgrad_col_3:
-#         smooth_head_3.write('SmoothGrad after attacked')
-#         heatmap_image_attacked, masked_image_attacked, attacked_mask= generate_images(st.session_state.image_id, epsilon=epsilon)
-#         st.image(heatmap_image_attacked)
-#         st.image(masked_image_attacked)
-    
-#     with smoothgrad_col_2:
-#         st.image(LoadImage('frontend/images/minus-sign-5.png'))
-
-#     with smoothgrad_col_5:
-#         smooth_head_5.write('SmoothGrad difference')
-#         difference_mask = abs(attacked_mask-mask)
-#         st.image(ShowHeatMap(difference_mask))
-#         masked_image = ShowMaskedImage(difference_mask, perturbed_image)
-#         st.image(masked_image)
+with smoothgrad_col_1:
+    st.image(images[0])
+    smooth_head_1.write(f'Change of {np.round(lambdas[0], 2)}')
 
-#     with smoothgrad_col_4:
-#         st.image(LoadImage('frontend/images/equal-sign.png'))
+with smoothgrad_col_2:
+    st.image(images[1])
+    smooth_head_2.write(f'Change of {np.round(lambdas[2], 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)}')