Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10053794831037521
Inter Cos: 0.12271284312009811
Norm Quadratic Average: 32.3537712097168
Nearest Class Center Accuracy: 0.83325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14608211815357208
Inter Cos: 0.14209656417369843
Norm Quadratic Average: 22.251070022583008
Nearest Class Center Accuracy: 0.858625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14991384744644165
Inter Cos: 0.13460677862167358
Norm Quadratic Average: 21.685142517089844
Nearest Class Center Accuracy: 0.879125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19496139883995056
Inter Cos: 0.11761524528265
Norm Quadratic Average: 13.205751419067383
Nearest Class Center Accuracy: 0.92975

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2217002660036087
Inter Cos: 0.11328805983066559
Norm Quadratic Average: 13.638269424438477
Nearest Class Center Accuracy: 0.961

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2914743423461914
Inter Cos: 0.10261650383472443
Norm Quadratic Average: 9.371293067932129
Nearest Class Center Accuracy: 0.995

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5378011465072632
Inter Cos: 0.1289079487323761
Norm Quadratic Average: 7.374058723449707
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.795780181884766
Linear Weight Rank: 4031
Intra Cos: 0.8489499688148499
Inter Cos: 0.13411769270896912
Norm Quadratic Average: 69.44047546386719
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.727279663085938
Linear Weight Rank: 3671
Intra Cos: 0.9389732480049133
Inter Cos: 0.15050479769706726
Norm Quadratic Average: 32.35783386230469
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5488197803497314
Linear Weight Rank: 10
Intra Cos: 0.9553508758544922
Inter Cos: 0.19639581441879272
Norm Quadratic Average: 18.224809646606445
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9635087251663208
Inter Cos: 0.31021881103515625
Norm Quadratic Average: 10.164525032043457
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07017082548141479
Accuracy: 0.9815
NC1 Within Class Collapse: 1.0096075534820557
NC2 Equinorm: Features: 0.08187846839427948, Weights: 0.020420579239726067
NC2 Equiangle: Features: 0.2192731433444553, Weights: 0.10553975635104709
NC3 Self-Duality: 0.18320351839065552
NC4 NCC Mismatch: 0.0024999999999999467

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792192697525
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12358955293893814
Inter Cos: 0.12962494790554047
Norm Quadratic Average: 31.92399024963379
Nearest Class Center Accuracy: 0.8245

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15568092465400696
Inter Cos: 0.1525277942419052
Norm Quadratic Average: 22.10698127746582
Nearest Class Center Accuracy: 0.8515

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15543639659881592
Inter Cos: 0.15327928960323334
Norm Quadratic Average: 21.55837059020996
Nearest Class Center Accuracy: 0.8755

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18306668102741241
Inter Cos: 0.1334111988544464
Norm Quadratic Average: 13.180032730102539
Nearest Class Center Accuracy: 0.919

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20743180811405182
Inter Cos: 0.13424138724803925
Norm Quadratic Average: 13.640631675720215
Nearest Class Center Accuracy: 0.9425

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28335002064704895
Inter Cos: 0.10965325683355331
Norm Quadratic Average: 9.33734130859375
Nearest Class Center Accuracy: 0.9715

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47608470916748047
Inter Cos: 0.14455178380012512
Norm Quadratic Average: 7.27577543258667
Nearest Class Center Accuracy: 0.9815

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.795780181884766
Linear Weight Rank: 4031
Intra Cos: 0.731986403465271
Inter Cos: 0.15495027601718903
Norm Quadratic Average: 66.87762451171875
Nearest Class Center Accuracy: 0.9805

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.727279663085938
Linear Weight Rank: 3671
Intra Cos: 0.822284460067749
Inter Cos: 0.17337800562381744
Norm Quadratic Average: 31.0454158782959
Nearest Class Center Accuracy: 0.9815

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5488197803497314
Linear Weight Rank: 10
Intra Cos: 0.8368446826934814
Inter Cos: 0.19873148202896118
Norm Quadratic Average: 17.510805130004883
Nearest Class Center Accuracy: 0.9815

Output Layer:
Intra Cos: 0.8425175547599792
Inter Cos: 0.3009335398674011
Norm Quadratic Average: 9.747593879699707
Nearest Class Center Accuracy: 0.9815

