Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 0.10067212581634521
Inter Cos: 0.12371665984392166
Norm Quadratic Average: 75.66156768798828
Nearest Class Center Accuracy: 0.830625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1425165832042694
Inter Cos: 0.13839933276176453
Norm Quadratic Average: 50.01231384277344
Nearest Class Center Accuracy: 0.85875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14170603454113007
Inter Cos: 0.13227862119674683
Norm Quadratic Average: 49.96765899658203
Nearest Class Center Accuracy: 0.871375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16793271899223328
Inter Cos: 0.11395294964313507
Norm Quadratic Average: 30.645488739013672
Nearest Class Center Accuracy: 0.910375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17520670592784882
Inter Cos: 0.10677868127822876
Norm Quadratic Average: 31.514650344848633
Nearest Class Center Accuracy: 0.934125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1987902969121933
Inter Cos: 0.11606098711490631
Norm Quadratic Average: 21.832517623901367
Nearest Class Center Accuracy: 0.976625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2959131598472595
Inter Cos: 0.08847609162330627
Norm Quadratic Average: 16.70309066772461
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79714965820312
Linear Weight Rank: 4031
Intra Cos: 0.5087893009185791
Inter Cos: 0.11840318143367767
Norm Quadratic Average: 107.42552947998047
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.49491500854492
Linear Weight Rank: 3670
Intra Cos: 0.6532890796661377
Inter Cos: 0.13500183820724487
Norm Quadratic Average: 54.52129364013672
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.05482816696167
Linear Weight Rank: 10
Intra Cos: 0.7775530815124512
Inter Cos: 0.16792155802249908
Norm Quadratic Average: 33.172054290771484
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9087337255477905
Inter Cos: 0.2507266402244568
Norm Quadratic Average: 17.245580673217773
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08636941468715667
Accuracy: 0.9755
NC1 Within Class Collapse: 1.6187055110931396
NC2 Equinorm: Features: 0.0655890554189682, Weights: 0.011746995151042938
NC2 Equiangle: Features: 0.20000131395128037, Weights: 0.0910795635647244
NC3 Self-Duality: 0.574462890625
NC4 NCC Mismatch: 0.0050000000000000044

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: 0.12697061896324158
Inter Cos: 0.13225893676280975
Norm Quadratic Average: 74.62086486816406
Nearest Class Center Accuracy: 0.825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15351498126983643
Inter Cos: 0.15783023834228516
Norm Quadratic Average: 49.53409194946289
Nearest Class Center Accuracy: 0.8525

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14508141577243805
Inter Cos: 0.1461993157863617
Norm Quadratic Average: 49.548561096191406
Nearest Class Center Accuracy: 0.8675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15776336193084717
Inter Cos: 0.14018629491329193
Norm Quadratic Average: 30.54515838623047
Nearest Class Center Accuracy: 0.9005

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16259609162807465
Inter Cos: 0.12976913154125214
Norm Quadratic Average: 31.494728088378906
Nearest Class Center Accuracy: 0.9245

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20041503012180328
Inter Cos: 0.11703238636255264
Norm Quadratic Average: 21.764328002929688
Nearest Class Center Accuracy: 0.9495

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25910353660583496
Inter Cos: 0.11061602085828781
Norm Quadratic Average: 16.56689453125
Nearest Class Center Accuracy: 0.969

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79714965820312
Linear Weight Rank: 4031
Intra Cos: 0.4354771077632904
Inter Cos: 0.14963006973266602
Norm Quadratic Average: 104.9414291381836
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.49491500854492
Linear Weight Rank: 3670
Intra Cos: 0.5631564259529114
Inter Cos: 0.16504894196987152
Norm Quadratic Average: 52.94844055175781
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.05482816696167
Linear Weight Rank: 10
Intra Cos: 0.6703394651412964
Inter Cos: 0.17112894356250763
Norm Quadratic Average: 32.072391510009766
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7900953888893127
Inter Cos: 0.24648217856884003
Norm Quadratic Average: 16.598112106323242
Nearest Class Center Accuracy: 0.974

