Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1099233627319336
Inter Cos: 0.11922435462474823
Norm Quadratic Average: 1.8407098054885864
Nearest Class Center Accuracy: 0.8523

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1803901642560959
Inter Cos: 0.14622323215007782
Norm Quadratic Average: 0.9695630669593811
Nearest Class Center Accuracy: 0.9112

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23152466118335724
Inter Cos: 0.16964919865131378
Norm Quadratic Average: 0.6066766381263733
Nearest Class Center Accuracy: 0.9487833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.32594677805900574
Inter Cos: 0.1586073786020279
Norm Quadratic Average: 0.2361345738172531
Nearest Class Center Accuracy: 0.9868666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7169477939605713
Inter Cos: 0.24502819776535034
Norm Quadratic Average: 0.1632445901632309
Nearest Class Center Accuracy: 0.9988333333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8857867121696472
Inter Cos: 0.3814881145954132
Norm Quadratic Average: 0.22144876420497894
Nearest Class Center Accuracy: 0.99995

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9855713248252869
Inter Cos: 0.46701833605766296
Norm Quadratic Average: 0.5750419497489929
Nearest Class Center Accuracy: 0.99995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.8952370882034302
Linear Weight Rank: 7
Intra Cos: 0.9963052868843079
Inter Cos: 0.4300984740257263
Norm Quadratic Average: 21.341676712036133
Nearest Class Center Accuracy: 0.99995

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8960241079330444
Linear Weight Rank: 1453
Intra Cos: 0.9969521760940552
Inter Cos: 0.3663988411426544
Norm Quadratic Average: 15.295417785644531
Nearest Class Center Accuracy: 0.99995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8971614837646484
Linear Weight Rank: 8
Intra Cos: 0.9971770644187927
Inter Cos: 0.29645460844039917
Norm Quadratic Average: 11.109125137329102
Nearest Class Center Accuracy: 0.99995

Output Layer:
Intra Cos: 0.997126042842865
Inter Cos: 0.307314932346344
Norm Quadratic Average: 8.68128776550293
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.03138509015589953
Accuracy: 0.9946
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.043690275400877, Weights: 0.02360328659415245
NC2 Equiangle: Features: 0.2258943345811632, Weights: 0.20703129238552517
NC3 Self-Duality: 0.04431362450122833
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
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: 0.12014331668615341
Inter Cos: 0.11965281516313553
Norm Quadratic Average: 1.8338563442230225
Nearest Class Center Accuracy: 0.8657

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19309401512145996
Inter Cos: 0.14326313138008118
Norm Quadratic Average: 0.9663865566253662
Nearest Class Center Accuracy: 0.9209

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24457253515720367
Inter Cos: 0.16617430746555328
Norm Quadratic Average: 0.6062937378883362
Nearest Class Center Accuracy: 0.9533

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33872297406196594
Inter Cos: 0.15406140685081482
Norm Quadratic Average: 0.23598222434520721
Nearest Class Center Accuracy: 0.9849

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7186566591262817
Inter Cos: 0.2604513168334961
Norm Quadratic Average: 0.16348794102668762
Nearest Class Center Accuracy: 0.9935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8780074715614319
Inter Cos: 0.3888469934463501
Norm Quadratic Average: 0.22153837978839874
Nearest Class Center Accuracy: 0.9948

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.973742663860321
Inter Cos: 0.46121788024902344
Norm Quadratic Average: 0.5728093385696411
Nearest Class Center Accuracy: 0.9947

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.8952370882034302
Linear Weight Rank: 7
Intra Cos: 0.9822357296943665
Inter Cos: 0.4245888888835907
Norm Quadratic Average: 21.26091957092285
Nearest Class Center Accuracy: 0.9946

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8960241079330444
Linear Weight Rank: 1453
Intra Cos: 0.9833895564079285
Inter Cos: 0.3620242774486542
Norm Quadratic Average: 15.235729217529297
Nearest Class Center Accuracy: 0.9946

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8971614837646484
Linear Weight Rank: 8
Intra Cos: 0.9840275645256042
Inter Cos: 0.29305097460746765
Norm Quadratic Average: 11.065754890441895
Nearest Class Center Accuracy: 0.9947

Output Layer:
Intra Cos: 0.98433518409729
Inter Cos: 0.3059314489364624
Norm Quadratic Average: 8.645256996154785
Nearest Class Center Accuracy: 0.9948

