Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10612604022026062
Inter Cos: 0.12199494242668152
Norm Quadratic Average: 75.09234619140625
Nearest Class Center Accuracy: 0.82925

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14354920387268066
Inter Cos: 0.1367574781179428
Norm Quadratic Average: 49.125404357910156
Nearest Class Center Accuracy: 0.848125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1392948180437088
Inter Cos: 0.12707845866680145
Norm Quadratic Average: 49.15873718261719
Nearest Class Center Accuracy: 0.87225

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1660889983177185
Inter Cos: 0.12618814408779144
Norm Quadratic Average: 29.99703598022461
Nearest Class Center Accuracy: 0.90825

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18298839032649994
Inter Cos: 0.10752646625041962
Norm Quadratic Average: 31.01848793029785
Nearest Class Center Accuracy: 0.934

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19622887670993805
Inter Cos: 0.10696488618850708
Norm Quadratic Average: 20.99173355102539
Nearest Class Center Accuracy: 0.975625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30406850576400757
Inter Cos: 0.09072087705135345
Norm Quadratic Average: 16.35102653503418
Nearest Class Center Accuracy: 0.997

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.7906494140625
Linear Weight Rank: 4031
Intra Cos: 0.522726833820343
Inter Cos: 0.09955031424760818
Norm Quadratic Average: 106.69151306152344
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.4929313659668
Linear Weight Rank: 3671
Intra Cos: 0.675957441329956
Inter Cos: 0.13107118010520935
Norm Quadratic Average: 54.51527786254883
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.06054949760437
Linear Weight Rank: 10
Intra Cos: 0.7937428951263428
Inter Cos: 0.1758803278207779
Norm Quadratic Average: 33.088584899902344
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.918287992477417
Inter Cos: 0.29643726348876953
Norm Quadratic Average: 17.447782516479492
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09179455149173736
Accuracy: 0.9735
NC1 Within Class Collapse: 1.634511947631836
NC2 Equinorm: Features: 0.074512779712677, Weights: 0.014077696017920971
NC2 Equiangle: Features: 0.20494314829508464, Weights: 0.08586061265733506
NC3 Self-Duality: 0.5801054239273071
NC4 NCC Mismatch: 0.00649999999999995

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: 0.1272190809249878
Inter Cos: 0.13416512310504913
Norm Quadratic Average: 73.95702362060547
Nearest Class Center Accuracy: 0.821

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15918292105197906
Inter Cos: 0.15371307730674744
Norm Quadratic Average: 48.72635269165039
Nearest Class Center Accuracy: 0.8385

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15661999583244324
Inter Cos: 0.13789881765842438
Norm Quadratic Average: 48.61483383178711
Nearest Class Center Accuracy: 0.864

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17626313865184784
Inter Cos: 0.15872225165367126
Norm Quadratic Average: 29.82839012145996
Nearest Class Center Accuracy: 0.9

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18750663101673126
Inter Cos: 0.1338689774274826
Norm Quadratic Average: 30.893016815185547
Nearest Class Center Accuracy: 0.923

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19287997484207153
Inter Cos: 0.11761348694562912
Norm Quadratic Average: 20.87738609313965
Nearest Class Center Accuracy: 0.9505

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28433680534362793
Inter Cos: 0.09887135028839111
Norm Quadratic Average: 16.192895889282227
Nearest Class Center Accuracy: 0.967

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.7906494140625
Linear Weight Rank: 4031
Intra Cos: 0.4483579099178314
Inter Cos: 0.11587273329496384
Norm Quadratic Average: 103.88409423828125
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.4929313659668
Linear Weight Rank: 3671
Intra Cos: 0.5800111293792725
Inter Cos: 0.15578144788742065
Norm Quadratic Average: 52.704925537109375
Nearest Class Center Accuracy: 0.9735

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.06054949760437
Linear Weight Rank: 10
Intra Cos: 0.6881349086761475
Inter Cos: 0.19345101714134216
Norm Quadratic Average: 31.857763290405273
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.8074582815170288
Inter Cos: 0.283063679933548
Norm Quadratic Average: 16.70806884765625
Nearest Class Center Accuracy: 0.9695

