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_0.0001.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: 0.09619331359863281
Inter Cos: 0.10927347838878632
Norm Quadratic Average: 59.90199661254883
Nearest Class Center Accuracy: 0.8408333333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16790848970413208
Inter Cos: 0.12829039990901947
Norm Quadratic Average: 42.37232208251953
Nearest Class Center Accuracy: 0.8932

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18966169655323029
Inter Cos: 0.13802653551101685
Norm Quadratic Average: 40.47613525390625
Nearest Class Center Accuracy: 0.9230166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24754983186721802
Inter Cos: 0.11375909298658371
Norm Quadratic Average: 26.826772689819336
Nearest Class Center Accuracy: 0.9731833333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3194311857223511
Inter Cos: 0.11956211179494858
Norm Quadratic Average: 28.966785430908203
Nearest Class Center Accuracy: 0.99035

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4557812809944153
Inter Cos: 0.18930529057979584
Norm Quadratic Average: 22.398393630981445
Nearest Class Center Accuracy: 0.9989

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7047699689865112
Inter Cos: 0.18204747140407562
Norm Quadratic Average: 17.222286224365234
Nearest Class Center Accuracy: 0.99995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 68.83158874511719
Linear Weight Rank: 4031
Intra Cos: 0.8783907294273376
Inter Cos: 0.09975869953632355
Norm Quadratic Average: 117.89408874511719
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 27.97420310974121
Linear Weight Rank: 3669
Intra Cos: 0.9732022881507874
Inter Cos: 0.022757653146982193
Norm Quadratic Average: 69.00607299804688
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4458212852478027
Linear Weight Rank: 10
Intra Cos: 0.9735535979270935
Inter Cos: 0.009229546412825584
Norm Quadratic Average: 34.3945198059082
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9970865249633789
Inter Cos: 0.20644046366214752
Norm Quadratic Average: 20.68527603149414
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0258322883938009
Accuracy: 0.9944
NC1 Within Class Collapse: 0.36464840173721313
NC2 Equinorm: Features: 0.06511205434799194, Weights: 0.016673212870955467
NC2 Equiangle: Features: 0.0567498419019911, Weights: 0.07083668178982205
NC3 Self-Duality: 0.5687354207038879
NC4 NCC Mismatch: 0.0012999999999999678

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: 0.10684368759393692
Inter Cos: 0.10938125103712082
Norm Quadratic Average: 59.53377914428711
Nearest Class Center Accuracy: 0.8533

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18052123486995697
Inter Cos: 0.13075418770313263
Norm Quadratic Average: 42.053070068359375
Nearest Class Center Accuracy: 0.9051

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2055130898952484
Inter Cos: 0.13554249703884125
Norm Quadratic Average: 40.219425201416016
Nearest Class Center Accuracy: 0.9317

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25990423560142517
Inter Cos: 0.10877577215433121
Norm Quadratic Average: 26.710289001464844
Nearest Class Center Accuracy: 0.9733

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33123499155044556
Inter Cos: 0.12587285041809082
Norm Quadratic Average: 28.89451026916504
Nearest Class Center Accuracy: 0.9873

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46014752984046936
Inter Cos: 0.18919526040554047
Norm Quadratic Average: 22.39108657836914
Nearest Class Center Accuracy: 0.9912

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7007909417152405
Inter Cos: 0.17965897917747498
Norm Quadratic Average: 17.242998123168945
Nearest Class Center Accuracy: 0.993

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 68.83158874511719
Linear Weight Rank: 4031
Intra Cos: 0.8687397837638855
Inter Cos: 0.09972940385341644
Norm Quadratic Average: 118.1431655883789
Nearest Class Center Accuracy: 0.9921

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 27.97420310974121
Linear Weight Rank: 3669
Intra Cos: 0.9521997570991516
Inter Cos: 0.02031909115612507
Norm Quadratic Average: 69.11771392822266
Nearest Class Center Accuracy: 0.9931

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4458212852478027
Linear Weight Rank: 10
Intra Cos: 0.9466311931610107
Inter Cos: 0.019321026280522346
Norm Quadratic Average: 34.46107482910156
Nearest Class Center Accuracy: 0.9938

Output Layer:
Intra Cos: 0.9791880249977112
Inter Cos: 0.21179580688476562
Norm Quadratic Average: 20.70492172241211
Nearest Class Center Accuracy: 0.9941

