Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0003.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: 0.10619332641363144
Inter Cos: 0.12211699783802032
Norm Quadratic Average: 85.4917221069336
Nearest Class Center Accuracy: 0.829125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14320604503154755
Inter Cos: 0.13600066304206848
Norm Quadratic Average: 55.93933868408203
Nearest Class Center Accuracy: 0.8475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13803128898143768
Inter Cos: 0.12607331573963165
Norm Quadratic Average: 56.11371994018555
Nearest Class Center Accuracy: 0.869875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1649307757616043
Inter Cos: 0.12265955656766891
Norm Quadratic Average: 34.28678512573242
Nearest Class Center Accuracy: 0.90525

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17905929684638977
Inter Cos: 0.10860516130924225
Norm Quadratic Average: 35.371192932128906
Nearest Class Center Accuracy: 0.931375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19006046652793884
Inter Cos: 0.1124887615442276
Norm Quadratic Average: 23.923490524291992
Nearest Class Center Accuracy: 0.972875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28477320075035095
Inter Cos: 0.09257230907678604
Norm Quadratic Average: 18.55837059020996
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.92973327636719
Linear Weight Rank: 4031
Intra Cos: 0.48458969593048096
Inter Cos: 0.1049230769276619
Norm Quadratic Average: 117.73667907714844
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39743423461914
Linear Weight Rank: 3671
Intra Cos: 0.6270800828933716
Inter Cos: 0.13736021518707275
Norm Quadratic Average: 63.98163986206055
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.27844500541687
Linear Weight Rank: 10
Intra Cos: 0.7482651472091675
Inter Cos: 0.16525673866271973
Norm Quadratic Average: 40.92915344238281
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9082556962966919
Inter Cos: 0.2907436788082123
Norm Quadratic Average: 22.439571380615234
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.11541862869262695
Accuracy: 0.971
NC1 Within Class Collapse: 1.7420730590820312
NC2 Equinorm: Features: 0.07126449048519135, Weights: 0.013121669180691242
NC2 Equiangle: Features: 0.2073703342013889, Weights: 0.08743466271294488
NC3 Self-Duality: 0.6387720108032227
NC4 NCC Mismatch: 0.008499999999999952

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: 0.12726819515228271
Inter Cos: 0.13421109318733215
Norm Quadratic Average: 84.18962860107422
Nearest Class Center Accuracy: 0.821

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15844190120697021
Inter Cos: 0.15294668078422546
Norm Quadratic Average: 55.505680084228516
Nearest Class Center Accuracy: 0.8395

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15456362068653107
Inter Cos: 0.13732224702835083
Norm Quadratic Average: 55.50670623779297
Nearest Class Center Accuracy: 0.8645

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17407667636871338
Inter Cos: 0.15720856189727783
Norm Quadratic Average: 34.100975036621094
Nearest Class Center Accuracy: 0.898

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.183048278093338
Inter Cos: 0.1364527940750122
Norm Quadratic Average: 35.21554183959961
Nearest Class Center Accuracy: 0.9185

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1886383444070816
Inter Cos: 0.1283121556043625
Norm Quadratic Average: 23.786962509155273
Nearest Class Center Accuracy: 0.948

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2699315547943115
Inter Cos: 0.09581636637449265
Norm Quadratic Average: 18.363353729248047
Nearest Class Center Accuracy: 0.964

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.92973327636719
Linear Weight Rank: 4031
Intra Cos: 0.4160584509372711
Inter Cos: 0.1112360879778862
Norm Quadratic Average: 114.63509368896484
Nearest Class Center Accuracy: 0.9735

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39743423461914
Linear Weight Rank: 3671
Intra Cos: 0.537385106086731
Inter Cos: 0.15035007894039154
Norm Quadratic Average: 61.83737564086914
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.27844500541687
Linear Weight Rank: 10
Intra Cos: 0.6479865908622742
Inter Cos: 0.18412305414676666
Norm Quadratic Average: 39.358707427978516
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.7977211475372314
Inter Cos: 0.28638720512390137
Norm Quadratic Average: 21.42463493347168
Nearest Class Center Accuracy: 0.9705

