Model save path: ./New_Models/bn_False_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: 0.11311887204647064
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: 0.11239708214998245
Inter Cos: 0.13064813613891602
Norm Quadratic Average: 43.16360092163086
Nearest Class Center Accuracy: 0.8215

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15779425203800201
Inter Cos: 0.16621841490268707
Norm Quadratic Average: 40.93742752075195
Nearest Class Center Accuracy: 0.81125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17851859331130981
Inter Cos: 0.1834750771522522
Norm Quadratic Average: 51.310447692871094
Nearest Class Center Accuracy: 0.82275

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19840550422668457
Inter Cos: 0.18507203459739685
Norm Quadratic Average: 32.905006408691406
Nearest Class Center Accuracy: 0.8565

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22600284218788147
Inter Cos: 0.20288652181625366
Norm Quadratic Average: 29.468944549560547
Nearest Class Center Accuracy: 0.903

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3009518086910248
Inter Cos: 0.1829925775527954
Norm Quadratic Average: 16.858169555664062
Nearest Class Center Accuracy: 0.94625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43589723110198975
Inter Cos: 0.23365099728107452
Norm Quadratic Average: 12.615918159484863
Nearest Class Center Accuracy: 0.981375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80001068115234
Linear Weight Rank: 4031
Intra Cos: 0.6554967164993286
Inter Cos: 0.2751377522945404
Norm Quadratic Average: 55.99770736694336
Nearest Class Center Accuracy: 0.997625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50486373901367
Linear Weight Rank: 3671
Intra Cos: 0.7442906498908997
Inter Cos: 0.2755397856235504
Norm Quadratic Average: 36.86302185058594
Nearest Class Center Accuracy: 0.99925

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.343696355819702
Linear Weight Rank: 10
Intra Cos: 0.7759958505630493
Inter Cos: 0.26727044582366943
Norm Quadratic Average: 28.907072067260742
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.7974166870117188
Inter Cos: 0.32435595989227295
Norm Quadratic Average: 21.263145446777344
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.07285808242857456
Accuracy: 0.979
NC1 Within Class Collapse: 1.8441429138183594
NC2 Equinorm: Features: 0.11723358184099197, Weights: 0.01593707501888275
NC2 Equiangle: Features: 0.2583651648627387, Weights: 0.10488931867811414
NC3 Self-Duality: 0.4737049639225006
NC4 NCC Mismatch: 0.009499999999999953

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: 0.13367663323879242
Inter Cos: 0.14812716841697693
Norm Quadratic Average: 42.30912399291992
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17255918681621552
Inter Cos: 0.20385417342185974
Norm Quadratic Average: 40.18437957763672
Nearest Class Center Accuracy: 0.8135

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1816330850124359
Inter Cos: 0.222617045044899
Norm Quadratic Average: 50.35210037231445
Nearest Class Center Accuracy: 0.823

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1817002147436142
Inter Cos: 0.2174157202243805
Norm Quadratic Average: 32.28045654296875
Nearest Class Center Accuracy: 0.848

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20803327858448029
Inter Cos: 0.2347867786884308
Norm Quadratic Average: 28.986148834228516
Nearest Class Center Accuracy: 0.892

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2750193476676941
Inter Cos: 0.19914492964744568
Norm Quadratic Average: 16.54828453063965
Nearest Class Center Accuracy: 0.9345

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3894585072994232
Inter Cos: 0.22633366286754608
Norm Quadratic Average: 12.348023414611816
Nearest Class Center Accuracy: 0.959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80001068115234
Linear Weight Rank: 4031
Intra Cos: 0.592223584651947
Inter Cos: 0.25699153542518616
Norm Quadratic Average: 54.46023178100586
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50486373901367
Linear Weight Rank: 3671
Intra Cos: 0.6736420392990112
Inter Cos: 0.25115084648132324
Norm Quadratic Average: 35.76915740966797
Nearest Class Center Accuracy: 0.9775

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.343696355819702
Linear Weight Rank: 10
Intra Cos: 0.7005866765975952
Inter Cos: 0.25605449080467224
Norm Quadratic Average: 28.073198318481445
Nearest Class Center Accuracy: 0.9785

Output Layer:
Intra Cos: 0.712138831615448
Inter Cos: 0.3344779908657074
Norm Quadratic Average: 20.63592529296875
Nearest Class Center Accuracy: 0.976

