updated color names

DisentanglementBase.py

@@ -366,6 +366,7 @@ class DisentanglementBase:
                 axs[i].set_title(np.round(lambd, 2))
             plt.tight_layout()
             plt.savefig(join(self.repo_folder, 'figures', name+'.jpg'))
+            plt.close()
         return images, lambdas
     
     def get_verification_score(self, separation_vector, feature_id, samples=10, lambd=1, savefig=False, feature=None, method=None):
@@ -377,21 +378,26 @@ class DisentanglementBase:
         
         for seed in tqdm(items):
             images, lambdas = self.generate_changes(seed, separation_vector, min_epsilon=-lambd, max_epsilon=lambd, count=3, savefig=savefig, feature=feature, method=method)
-            colors_negative = extract_color(images[0], 5, 1, None)
-            h0, s0, v0 = ImageColor.getcolor(colors_negative[0], 'HSV')
+            try:
+                colors_negative = extract_color(images[0], 5, 1, None)
+                h0, s0, v0 = ImageColor.getcolor(colors_negative[0], 'HSV')
             
-            colors_orig = extract_color(images[1], 5, 1, None)
-            h1, s1, v1 = ImageColor.getcolor(colors_orig[0], 'HSV')
-            
-            colors_positive = extract_color(images[2], 5, 1, None)
-            h2, s2, v2 = ImageColor.getcolor(colors_positive[0], 'HSV')
+                colors_orig = extract_color(images[1], 5, 1, None)
+                h1, s1, v1 = ImageColor.getcolor(colors_orig[0], 'HSV')
+                
+                colors_positive = extract_color(images[2], 5, 1, None)
+                h2, s2, v2 = ImageColor.getcolor(colors_positive[0], 'HSV')
+                
+                if h1 > hue_low and h1 < hue_high:
+                    samples -= 1
+                else:
+                    if (h0 > hue_low and h0 < hue_high) or (h2 > hue_low and h2 < hue_high):
+                        matches += 1
             
-            if h1 > hue_low and h1 < hue_high:
-                samples -= 1
-            else:
-                if (h0 > hue_low and h0 < hue_high) or (h2 > hue_low and h2 < hue_high):
-                    matches += 1
+            except Exception as e:
+                print(e)
         
+                
         return np.round(matches / samples, 2)
     
 
@@ -408,18 +414,18 @@ def main():
     with dnnlib.util.open_url(model_file) as f:
         model = legacy.load_network_pkl(f)['G_ema'] # type: ignore
 
-    colors_list = ['Warm Pink Red', 'Red Orange', 'Orange Yellow', 'Gold Yellow', 'Chartreuse Green',
-                   'Kelly Green', 'Green Blue Seafoam', 'Blue Green Cyan',
-                   'Warm Blue', 'Indigo Blue Purple', 'Purple Magenta', 'Magenta Pink']
+    colors_list = ['Red', 'Orange', 'Yellow', 'Yellow Green', 'Chartreuse Green',
+                   'Kelly Green', 'Green Blue Seafoam', 'Cyan Blue',
+                   'Warm Blue', 'Indigo', 'Purple Magenta', 'Magenta Pink']
     
     scores = []
-    kwargs = {'CL method':['LR', 'SVM'], 'C':[0.1, 1], 'sign':[True, False], 'num_factors':[1, 10, 20, 50], 'cutout': [None, 0.2], 'max_lambda':[6, 10, 1], 'samples':50, 'lambda_verif':[1, 3, 6]}
+    kwargs = {'CL method':['LR', 'SVM'], 'C':[0.1, 1], 'sign':[True, False], 'num_factors':[1, 10, 20], 'cutout': [None], 'max_lambda':[18, 3], 'samples':50, 'lambda_verif':[10, 5, 3]}
     
     for space in ['w', 'z', 's']:
         print('Launching experiment with space:', space)
         disentanglemnet_exp = DisentanglementBase(repo_folder, model, annotations, df, space=space, colors_list=colors_list, compute_s=False)
 
-        for method in ['StyleSpace', 'InterFaceGAN', 'GANSpace']:
+        for method in ['InterFaceGAN', 'StyleSpace', 'GANSpace']:
             if space != 's' and method == 'InterFaceGAN':
                 print('Now obtaining separation vector for using InterfaceGAN')
                 for met in kwargs['CL method']:
@@ -427,17 +433,22 @@ def main():
                         separation_vectors = disentanglemnet_exp.InterFaceGAN_separation_vector(method=met, C=c)
                         for i, color in enumerate(colors_list):
                             print('Generating images with variations')
-                            seed = random.randint(0,100000)
-                            for eps in kwargs['max_lambda']:
-                                disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=method)
-                            
+                            for s in range(30):
+                                seed = random.randint(0,100000)
+                                for eps in kwargs['max_lambda']:
+                                    disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=str(method) + '_' + str(met) + '_' + str(c))
+                                
                             print('Finally obtaining verification score')
                             for verif in kwargs['lambda_verif']:    
-                                score = disentanglemnet_exp.get_verification_score(separation_vectors[i], i, samples=kwargs['samples'], lambd=verif, savefig=True, feature=color, method=method)
+                                score = disentanglemnet_exp.get_verification_score(separation_vectors[i], i, samples=kwargs['samples'], lambd=verif, savefig=False, feature=color, method=method)
                                 print('Score for method', method, 'on space', space, 'for color', color, ':', score)
                             
-                                scores.append([space, method, color, score, 'classification method:' + met + ', regularization: ' + str(c) + ', verification lambda:' + str(verif)])
-            
+                                scores.append([space, method, color, score, 'classification method:' + met + ', regularization: ' + str(c) + ', verification lambda:' + str(verif), ', '.join(list(separation_vectors[i].astype(str)))])
+                        score_df = pd.DataFrame(scores, columns=['space', 'method', 'color', 'score', 'kwargs', 'vector'])
+                        print(score_df)
+                        score_df.to_csv(join(repo_folder, 'data/scores.csv'))
+                    
+                        
             elif method == 'StyleSpace':
                 print('Now obtaining separation vector for using StyleSpace')
                 for sign in kwargs['sign']:
@@ -446,35 +457,40 @@ def main():
                             separation_vectors = disentanglemnet_exp.StyleSpace_separation_vector(sign=sign, num_factors=num_factors, cutout=cutout)
                             for i, color in enumerate(colors_list):
                                 print('Generating images with variations')
-                                seed = random.randint(0,100000)
-                                for eps in kwargs['max_lambda']:
-                                    disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=method)
-                                        
+                                for s in range(30):
+                                    seed = random.randint(0,100000)
+                                    for eps in kwargs['max_lambda']:
+                                        disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=method + '_' + str(num_factors) + '_' + str(cutout) + '_' + str(sign))
+                                            
                                 print('Finally obtaining verification score')
                                 for verif in kwargs['lambda_verif']:    
-                                    score = disentanglemnet_exp.get_verification_score(separation_vectors[i], i, samples=kwargs['samples'], lambd=verif, savefig=True, feature=color, method=method)
+                                    score = disentanglemnet_exp.get_verification_score(separation_vectors[i], i, samples=kwargs['samples'], lambd=verif, savefig=False, feature=color, method=method)
                                     print('Score for method', method, 'on space', space, 'for color', color, ':', score)
                                         
-                                    scores.append([space, method, color, score, 'using sign:' + str(sign) + ', number of factors: ' + str(num_factors) + ', using cutout: ' + str(cutout) + ', verification lambda:' + str(verif)])
-                                    
+                                    scores.append([space, method, color, score, 'using sign:' + str(sign) + ', number of factors: ' + str(num_factors) + ', using cutout: ' + str(cutout) + ', verification lambda:' + str(verif), ', '.join(list(separation_vectors[i].astype(str)))])
+                            score_df = pd.DataFrame(scores, columns=['space', 'method', 'color', 'score', 'kwargs', 'vector'])
+                            print(score_df)
+                            score_df.to_csv(join(repo_folder, 'data/scores.csv'))
+                            
             if space == 'w' and method == 'GANSpace':
                 print('Now obtaining separation vector for using GANSpace')
                 separation_vectors = disentanglemnet_exp.GANSpace_separation_vectors(100)
-                for i in range(100):
+                for s in range(30):
                     print('Generating images with variations')
                     seed = random.randint(0,100000)
-                    for eps in kwargs['max_lambda']:
-                        disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=method)
-                                
-                    score = None
-                    scores.append([space, method, color, score, '100'])
+                    for i in range(100):
+                        for eps in kwargs['max_lambda']:
+                            disentanglemnet_exp.generate_changes(seed, separation_vectors[i], min_epsilon=-eps, max_epsilon=eps, savefig=True, feature=color, method=method)
+                                        
+                score = None
+                scores.append([space, method, color, score, '100', ', '.join(list(separation_vectors[i].astype(str)))])
             else:
                 print('Skipping', method, 'on space', space)
                 continue
             
             
     
-    score_df = pd.DataFrame(scores, columns=['space', 'method', 'color', 'score', 'kwargs'])
+    score_df = pd.DataFrame(scores, columns=['space', 'method', 'color', 'score', 'kwargs', 'vector'])
     print(score_df)
     score_df.to_csv(join(repo_folder, 'data/scores.csv'))