Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09782630205154419
Inter Cos: 0.10052018612623215
Norm Quadratic Average: 2.738292932510376
Nearest Class Center Accuracy: 0.8551833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18052946031093597
Inter Cos: 0.13394084572792053
Norm Quadratic Average: 1.4783046245574951
Nearest Class Center Accuracy: 0.91295

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2240074723958969
Inter Cos: 0.15168295800685883
Norm Quadratic Average: 0.9637258648872375
Nearest Class Center Accuracy: 0.9525666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31579986214637756
Inter Cos: 0.13408753275871277
Norm Quadratic Average: 0.4981396496295929
Nearest Class Center Accuracy: 0.9885333333333334

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6240223050117493
Inter Cos: 0.22141659259796143
Norm Quadratic Average: 0.4101337492465973
Nearest Class Center Accuracy: 0.9994

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8086118102073669
Inter Cos: 0.2019585520029068
Norm Quadratic Average: 0.5702065825462341
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9781858325004578
Inter Cos: 0.1447596549987793
Norm Quadratic Average: 0.9802672266960144
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1216447353363037
Linear Weight Rank: 13
Intra Cos: 0.9959618449211121
Inter Cos: 0.253783255815506
Norm Quadratic Average: 23.357513427734375
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.123544931411743
Linear Weight Rank: 1163
Intra Cos: 0.9975453615188599
Inter Cos: 0.23033340275287628
Norm Quadratic Average: 17.059701919555664
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1236464977264404
Linear Weight Rank: 9
Intra Cos: 0.9980868101119995
Inter Cos: 0.17678864300251007
Norm Quadratic Average: 12.782621383666992
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9978175759315491
Inter Cos: 0.19720982015132904
Norm Quadratic Average: 10.311684608459473
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015323799245804548
Accuracy: 0.9962
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03196870535612106, Weights: 0.0070135463029146194
NC2 Equiangle: Features: 0.16984904607137044, Weights: 0.15299438900417753
NC3 Self-Duality: 0.032438553869724274
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10797280818223953
Inter Cos: 0.1007893905043602
Norm Quadratic Average: 2.7225840091705322
Nearest Class Center Accuracy: 0.8679

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19222398102283478
Inter Cos: 0.13172051310539246
Norm Quadratic Average: 1.4705383777618408
Nearest Class Center Accuracy: 0.9228

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23833009600639343
Inter Cos: 0.1485022008419037
Norm Quadratic Average: 0.9605889320373535
Nearest Class Center Accuracy: 0.9561

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3271048665046692
Inter Cos: 0.1499340832233429
Norm Quadratic Average: 0.4963985085487366
Nearest Class Center Accuracy: 0.9863

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.627926766872406
Inter Cos: 0.23694971203804016
Norm Quadratic Average: 0.4090465009212494
Nearest Class Center Accuracy: 0.9934

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.802106499671936
Inter Cos: 0.21273833513259888
Norm Quadratic Average: 0.5681505799293518
Nearest Class Center Accuracy: 0.9961

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9689401388168335
Inter Cos: 0.15096363425254822
Norm Quadratic Average: 0.9757557511329651
Nearest Class Center Accuracy: 0.9964

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1216447353363037
Linear Weight Rank: 13
Intra Cos: 0.9794043898582458
Inter Cos: 0.2555231750011444
Norm Quadratic Average: 23.24049949645996
Nearest Class Center Accuracy: 0.9963

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.123544931411743
Linear Weight Rank: 1163
Intra Cos: 0.9816530346870422
Inter Cos: 0.23279187083244324
Norm Quadratic Average: 16.972225189208984
Nearest Class Center Accuracy: 0.9964

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1236464977264404
Linear Weight Rank: 9
Intra Cos: 0.9823765158653259
Inter Cos: 0.18071886897087097
Norm Quadratic Average: 12.716933250427246
Nearest Class Center Accuracy: 0.9964

Output Layer:
Intra Cos: 0.9848183393478394
Inter Cos: 0.19635836780071259
Norm Quadratic Average: 10.257735252380371
Nearest Class Center Accuracy: 0.9962

