Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09954998642206192
Inter Cos: 0.11624929308891296
Norm Quadratic Average: 85.33165740966797
Nearest Class Center Accuracy: 0.831875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1441762000322342
Inter Cos: 0.13327471911907196
Norm Quadratic Average: 57.01475524902344
Nearest Class Center Accuracy: 0.84675

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14853307604789734
Inter Cos: 0.12843027710914612
Norm Quadratic Average: 56.093727111816406
Nearest Class Center Accuracy: 0.8655

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17594167590141296
Inter Cos: 0.10201570391654968
Norm Quadratic Average: 34.98760223388672
Nearest Class Center Accuracy: 0.90275

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18189308047294617
Inter Cos: 0.09534482657909393
Norm Quadratic Average: 35.958980560302734
Nearest Class Center Accuracy: 0.929625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20827031135559082
Inter Cos: 0.11379691958427429
Norm Quadratic Average: 24.524059295654297
Nearest Class Center Accuracy: 0.971125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28623926639556885
Inter Cos: 0.11339938640594482
Norm Quadratic Average: 18.980897903442383
Nearest Class Center Accuracy: 0.995125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9305419921875
Linear Weight Rank: 4031
Intra Cos: 0.46584638953208923
Inter Cos: 0.14522980153560638
Norm Quadratic Average: 118.50971221923828
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39781951904297
Linear Weight Rank: 3670
Intra Cos: 0.6195890307426453
Inter Cos: 0.1793375015258789
Norm Quadratic Average: 64.12553405761719
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.289579153060913
Linear Weight Rank: 10
Intra Cos: 0.7416850924491882
Inter Cos: 0.1998233199119568
Norm Quadratic Average: 40.903343200683594
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8979493975639343
Inter Cos: 0.27108749747276306
Norm Quadratic Average: 22.41143798828125
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.11659332355856895
Accuracy: 0.975
NC1 Within Class Collapse: 1.7866159677505493
NC2 Equinorm: Features: 0.06293823570013046, Weights: 0.012120228260755539
NC2 Equiangle: Features: 0.2068309783935547, Weights: 0.08733386993408203
NC3 Self-Duality: 0.6407832503318787
NC4 NCC Mismatch: 0.006000000000000005

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: 0.12501730024814606
Inter Cos: 0.12887977063655853
Norm Quadratic Average: 84.34100341796875
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1559765338897705
Inter Cos: 0.16499893367290497
Norm Quadratic Average: 56.702640533447266
Nearest Class Center Accuracy: 0.8405

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.150728240609169
Inter Cos: 0.14956405758857727
Norm Quadratic Average: 55.86910629272461
Nearest Class Center Accuracy: 0.86

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17010614275932312
Inter Cos: 0.12185933440923691
Norm Quadratic Average: 34.96809387207031
Nearest Class Center Accuracy: 0.9015

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17358019948005676
Inter Cos: 0.11723094433546066
Norm Quadratic Average: 35.97710037231445
Nearest Class Center Accuracy: 0.924

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20711512863636017
Inter Cos: 0.12750431895256042
Norm Quadratic Average: 24.55473518371582
Nearest Class Center Accuracy: 0.943

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2632499933242798
Inter Cos: 0.11389172077178955
Norm Quadratic Average: 18.902494430541992
Nearest Class Center Accuracy: 0.9625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9305419921875
Linear Weight Rank: 4031
Intra Cos: 0.3999793529510498
Inter Cos: 0.14140839874744415
Norm Quadratic Average: 115.8884506225586
Nearest Class Center Accuracy: 0.972

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39781951904297
Linear Weight Rank: 3670
Intra Cos: 0.5135804414749146
Inter Cos: 0.17891906201839447
Norm Quadratic Average: 62.131927490234375
Nearest Class Center Accuracy: 0.973

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.289579153060913
Linear Weight Rank: 10
Intra Cos: 0.6194967031478882
Inter Cos: 0.21204645931720734
Norm Quadratic Average: 39.40850067138672
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7678003907203674
Inter Cos: 0.33514803647994995
Norm Quadratic Average: 21.434036254882812
Nearest Class Center Accuracy: 0.9715

