Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067839860916
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1011836975812912
Inter Cos: 0.1241292729973793
Norm Quadratic Average: 21.723169326782227
Nearest Class Center Accuracy: 0.833125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14961083233356476
Inter Cos: 0.14375263452529907
Norm Quadratic Average: 13.715219497680664
Nearest Class Center Accuracy: 0.85475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15915632247924805
Inter Cos: 0.14759644865989685
Norm Quadratic Average: 13.41312026977539
Nearest Class Center Accuracy: 0.878625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2106209546327591
Inter Cos: 0.13119152188301086
Norm Quadratic Average: 8.161646842956543
Nearest Class Center Accuracy: 0.93575

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23998184502124786
Inter Cos: 0.12218987196683884
Norm Quadratic Average: 8.213217735290527
Nearest Class Center Accuracy: 0.973125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3610058128833771
Inter Cos: 0.13772375881671906
Norm Quadratic Average: 5.641183853149414
Nearest Class Center Accuracy: 0.998375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.686845600605011
Inter Cos: 0.1444704234600067
Norm Quadratic Average: 4.685204029083252
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.994709014892578
Linear Weight Rank: 4031
Intra Cos: 0.9422807097434998
Inter Cos: 0.0936240553855896
Norm Quadratic Average: 53.012611389160156
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790581703186035
Linear Weight Rank: 3670
Intra Cos: 0.9816598296165466
Inter Cos: 0.11945471167564392
Norm Quadratic Average: 25.565698623657227
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.564988136291504
Linear Weight Rank: 10
Intra Cos: 0.9833829998970032
Inter Cos: 0.1625237613916397
Norm Quadratic Average: 14.431605339050293
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9861708283424377
Inter Cos: 0.2967228293418884
Norm Quadratic Average: 8.588326454162598
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07144078731536865
Accuracy: 0.983
NC1 Within Class Collapse: 0.8539412021636963
NC2 Equinorm: Features: 0.061220619827508926, Weights: 0.016031580045819283
NC2 Equiangle: Features: 0.2056221432156033, Weights: 0.11955937279595269
NC3 Self-Duality: 0.0888388603925705
NC4 NCC Mismatch: 0.0014999999999999458

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: 0.12771420180797577
Inter Cos: 0.13167643547058105
Norm Quadratic Average: 21.370853424072266
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16631999611854553
Inter Cos: 0.1626616269350052
Norm Quadratic Average: 13.54877758026123
Nearest Class Center Accuracy: 0.8545

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16652412712574005
Inter Cos: 0.15294553339481354
Norm Quadratic Average: 13.227778434753418
Nearest Class Center Accuracy: 0.878

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19904351234436035
Inter Cos: 0.13944046199321747
Norm Quadratic Average: 8.091599464416504
Nearest Class Center Accuracy: 0.924

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24063332378864288
Inter Cos: 0.14082449674606323
Norm Quadratic Average: 8.175893783569336
Nearest Class Center Accuracy: 0.953

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.334961861371994
Inter Cos: 0.14650368690490723
Norm Quadratic Average: 5.591244220733643
Nearest Class Center Accuracy: 0.9785

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6061397194862366
Inter Cos: 0.16473831236362457
Norm Quadratic Average: 4.575943470001221
Nearest Class Center Accuracy: 0.983

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.994709014892578
Linear Weight Rank: 4031
Intra Cos: 0.8470370769500732
Inter Cos: 0.12222982197999954
Norm Quadratic Average: 50.724735260009766
Nearest Class Center Accuracy: 0.983

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790581703186035
Linear Weight Rank: 3670
Intra Cos: 0.8827978372573853
Inter Cos: 0.1426500529050827
Norm Quadratic Average: 24.465269088745117
Nearest Class Center Accuracy: 0.984

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.564988136291504
Linear Weight Rank: 10
Intra Cos: 0.8805071115493774
Inter Cos: 0.1713680773973465
Norm Quadratic Average: 13.857542037963867
Nearest Class Center Accuracy: 0.9845

Output Layer:
Intra Cos: 0.8844351768493652
Inter Cos: 0.2965102195739746
Norm Quadratic Average: 8.248275756835938
Nearest Class Center Accuracy: 0.9845

