Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
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: 0.10112279653549194
Inter Cos: 0.1177535206079483
Norm Quadratic Average: 86.9267807006836
Nearest Class Center Accuracy: 0.8365

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15046557784080505
Inter Cos: 0.13836319744586945
Norm Quadratic Average: 52.974853515625
Nearest Class Center Accuracy: 0.85975

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15176692605018616
Inter Cos: 0.1270761340856552
Norm Quadratic Average: 55.12902069091797
Nearest Class Center Accuracy: 0.87775

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16863156855106354
Inter Cos: 0.10601315647363663
Norm Quadratic Average: 34.0842170715332
Nearest Class Center Accuracy: 0.912375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16876456141471863
Inter Cos: 0.09258634597063065
Norm Quadratic Average: 35.02471160888672
Nearest Class Center Accuracy: 0.938

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20080973207950592
Inter Cos: 0.08471211045980453
Norm Quadratic Average: 24.107086181640625
Nearest Class Center Accuracy: 0.976375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28636327385902405
Inter Cos: 0.093950055539608
Norm Quadratic Average: 18.26161766052246
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62254333496094
Linear Weight Rank: 4031
Intra Cos: 0.47805434465408325
Inter Cos: 0.1117134839296341
Norm Quadratic Average: 114.8756103515625
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.0581169128418
Linear Weight Rank: 3670
Intra Cos: 0.6208035945892334
Inter Cos: 0.12088707834482193
Norm Quadratic Average: 60.877166748046875
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2172110080718994
Linear Weight Rank: 10
Intra Cos: 0.7513909935951233
Inter Cos: 0.14403054118156433
Norm Quadratic Average: 37.98635482788086
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9089400768280029
Inter Cos: 0.2460760772228241
Norm Quadratic Average: 19.704879760742188
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09396544897556305
Accuracy: 0.976
NC1 Within Class Collapse: 1.6853910684585571
NC2 Equinorm: Features: 0.05003868415951729, Weights: 0.011120663955807686
NC2 Equiangle: Features: 0.17919614579942492, Weights: 0.08386161062452528
NC3 Self-Duality: 0.6305193305015564
NC4 NCC Mismatch: 0.010000000000000009

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.12355277687311172
Inter Cos: 0.12785817682743073
Norm Quadratic Average: 85.99560546875
Nearest Class Center Accuracy: 0.8325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1550310254096985
Inter Cos: 0.1607554852962494
Norm Quadratic Average: 52.71564865112305
Nearest Class Center Accuracy: 0.8545

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1462789624929428
Inter Cos: 0.14301925897598267
Norm Quadratic Average: 54.91539001464844
Nearest Class Center Accuracy: 0.87

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15875664353370667
Inter Cos: 0.11677629500627518
Norm Quadratic Average: 34.091617584228516
Nearest Class Center Accuracy: 0.908

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.158408522605896
Inter Cos: 0.11194407939910889
Norm Quadratic Average: 35.05470275878906
Nearest Class Center Accuracy: 0.9345

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18720267713069916
Inter Cos: 0.08748440444469452
Norm Quadratic Average: 24.090648651123047
Nearest Class Center Accuracy: 0.9565

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25834518671035767
Inter Cos: 0.10052210092544556
Norm Quadratic Average: 18.1776123046875
Nearest Class Center Accuracy: 0.9715

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62254333496094
Linear Weight Rank: 4031
Intra Cos: 0.42013999819755554
Inter Cos: 0.11730165034532547
Norm Quadratic Average: 112.89424896240234
Nearest Class Center Accuracy: 0.976

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.0581169128418
Linear Weight Rank: 3670
Intra Cos: 0.5429621338844299
Inter Cos: 0.13425365090370178
Norm Quadratic Average: 59.43679428100586
Nearest Class Center Accuracy: 0.9785

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2172110080718994
Linear Weight Rank: 10
Intra Cos: 0.6585476994514465
Inter Cos: 0.15521100163459778
Norm Quadratic Average: 36.95395278930664
Nearest Class Center Accuracy: 0.978

Output Layer:
Intra Cos: 0.8027668595314026
Inter Cos: 0.23131969571113586
Norm Quadratic Average: 19.06791114807129
Nearest Class Center Accuracy: 0.979

