Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.003.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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09970424324274063
Inter Cos: 0.11619192361831665
Norm Quadratic Average: 75.10739135742188
Nearest Class Center Accuracy: 0.831875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14493650197982788
Inter Cos: 0.13398031890392303
Norm Quadratic Average: 50.18779754638672
Nearest Class Center Accuracy: 0.8465

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1495249718427658
Inter Cos: 0.12949006259441376
Norm Quadratic Average: 49.24700164794922
Nearest Class Center Accuracy: 0.864375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17724275588989258
Inter Cos: 0.10294380784034729
Norm Quadratic Average: 30.67644691467285
Nearest Class Center Accuracy: 0.90325

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18543174862861633
Inter Cos: 0.0984223335981369
Norm Quadratic Average: 31.458267211914062
Nearest Class Center Accuracy: 0.9315

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21257269382476807
Inter Cos: 0.116763174533844
Norm Quadratic Average: 21.47605323791504
Nearest Class Center Accuracy: 0.974375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29952070116996765
Inter Cos: 0.1134859248995781
Norm Quadratic Average: 16.727750778198242
Nearest Class Center Accuracy: 0.99725

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79138946533203
Linear Weight Rank: 4031
Intra Cos: 0.4971809983253479
Inter Cos: 0.14209812879562378
Norm Quadratic Average: 107.13700866699219
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.493350982666016
Linear Weight Rank: 3670
Intra Cos: 0.6609619855880737
Inter Cos: 0.17238737642765045
Norm Quadratic Average: 54.39299774169922
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.071171998977661
Linear Weight Rank: 10
Intra Cos: 0.7870997190475464
Inter Cos: 0.1878841370344162
Norm Quadratic Average: 32.931724548339844
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9098227620124817
Inter Cos: 0.2798267900943756
Norm Quadratic Average: 17.335973739624023
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0959227147102356
Accuracy: 0.9715
NC1 Within Class Collapse: 1.6741580963134766
NC2 Equinorm: Features: 0.0673997551202774, Weights: 0.013690385967493057
NC2 Equiangle: Features: 0.20375162760416668, Weights: 0.0852094226413303
NC3 Self-Duality: 0.5780131220817566
NC4 NCC Mismatch: 0.007499999999999951

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.1251484900712967
Inter Cos: 0.12916778028011322
Norm Quadratic Average: 74.24052429199219
Nearest Class Center Accuracy: 0.828

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15688134729862213
Inter Cos: 0.16555926203727722
Norm Quadratic Average: 49.91373825073242
Nearest Class Center Accuracy: 0.842

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1520850956439972
Inter Cos: 0.15125218033790588
Norm Quadratic Average: 49.0599479675293
Nearest Class Center Accuracy: 0.861

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17286993563175201
Inter Cos: 0.12534332275390625
Norm Quadratic Average: 30.672927856445312
Nearest Class Center Accuracy: 0.901

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17897696793079376
Inter Cos: 0.11927793174982071
Norm Quadratic Average: 31.48853874206543
Nearest Class Center Accuracy: 0.923

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21336549520492554
Inter Cos: 0.12905555963516235
Norm Quadratic Average: 21.498672485351562
Nearest Class Center Accuracy: 0.945

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2783561050891876
Inter Cos: 0.1116563230752945
Norm Quadratic Average: 16.65345573425293
Nearest Class Center Accuracy: 0.9635

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79138946533203
Linear Weight Rank: 4031
Intra Cos: 0.43210431933403015
Inter Cos: 0.1365823894739151
Norm Quadratic Average: 104.6773452758789
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.493350982666016
Linear Weight Rank: 3670
Intra Cos: 0.5589334964752197
Inter Cos: 0.17113518714904785
Norm Quadratic Average: 52.68482208251953
Nearest Class Center Accuracy: 0.972

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.071171998977661
Linear Weight Rank: 10
Intra Cos: 0.6644110679626465
Inter Cos: 0.1994248777627945
Norm Quadratic Average: 31.755823135375977
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.7846189141273499
Inter Cos: 0.2996472418308258
Norm Quadratic Average: 16.62881851196289
Nearest Class Center Accuracy: 0.974

