Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0007.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: 0.11311888694763184
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: 0.10197992622852325
Inter Cos: 0.12107145041227341
Norm Quadratic Average: 80.13150787353516
Nearest Class Center Accuracy: 0.8385

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1493612676858902
Inter Cos: 0.14182627201080322
Norm Quadratic Average: 56.49745559692383
Nearest Class Center Accuracy: 0.85775

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14608792960643768
Inter Cos: 0.13022926449775696
Norm Quadratic Average: 57.13090515136719
Nearest Class Center Accuracy: 0.871625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17231303453445435
Inter Cos: 0.1094864159822464
Norm Quadratic Average: 34.171905517578125
Nearest Class Center Accuracy: 0.909

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18383197486400604
Inter Cos: 0.09673424810171127
Norm Quadratic Average: 35.037601470947266
Nearest Class Center Accuracy: 0.935375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2101334184408188
Inter Cos: 0.1300896257162094
Norm Quadratic Average: 23.892648696899414
Nearest Class Center Accuracy: 0.972375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28729623556137085
Inter Cos: 0.10243891179561615
Norm Quadratic Average: 18.493770599365234
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03782653808594
Linear Weight Rank: 4031
Intra Cos: 0.48723673820495605
Inter Cos: 0.13120876252651215
Norm Quadratic Average: 116.61741638183594
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.61960983276367
Linear Weight Rank: 3670
Intra Cos: 0.6332423090934753
Inter Cos: 0.15499207377433777
Norm Quadratic Average: 62.46531295776367
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.23240065574646
Linear Weight Rank: 10
Intra Cos: 0.7575308084487915
Inter Cos: 0.15979808568954468
Norm Quadratic Average: 39.38570022583008
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9113767147064209
Inter Cos: 0.23947826027870178
Norm Quadratic Average: 21.082868576049805
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08615320199728012
Accuracy: 0.9775
NC1 Within Class Collapse: 1.6602317094802856
NC2 Equinorm: Features: 0.05287867784500122, Weights: 0.011060306802392006
NC2 Equiangle: Features: 0.20812017652723525, Weights: 0.08374652332729764
NC3 Self-Duality: 0.6263285279273987
NC4 NCC Mismatch: 0.007000000000000006

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: 0.12086095660924911
Inter Cos: 0.1255674958229065
Norm Quadratic Average: 79.2525863647461
Nearest Class Center Accuracy: 0.8325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14710459113121033
Inter Cos: 0.14601412415504456
Norm Quadratic Average: 56.14944076538086
Nearest Class Center Accuracy: 0.846

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14730648696422577
Inter Cos: 0.13309474289417267
Norm Quadratic Average: 56.78813171386719
Nearest Class Center Accuracy: 0.8635

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1600164771080017
Inter Cos: 0.11184436082839966
Norm Quadratic Average: 34.07094192504883
Nearest Class Center Accuracy: 0.9

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17084498703479767
Inter Cos: 0.10204005986452103
Norm Quadratic Average: 34.970645904541016
Nearest Class Center Accuracy: 0.927

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19961407780647278
Inter Cos: 0.13215495645999908
Norm Quadratic Average: 23.831192016601562
Nearest Class Center Accuracy: 0.9515

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2615621089935303
Inter Cos: 0.09780304878950119
Norm Quadratic Average: 18.341779708862305
Nearest Class Center Accuracy: 0.969

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03782653808594
Linear Weight Rank: 4031
Intra Cos: 0.40962833166122437
Inter Cos: 0.13119550049304962
Norm Quadratic Average: 114.07965087890625
Nearest Class Center Accuracy: 0.976

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.61960983276367
Linear Weight Rank: 3670
Intra Cos: 0.5329946875572205
Inter Cos: 0.16025741398334503
Norm Quadratic Average: 60.735408782958984
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.23240065574646
Linear Weight Rank: 10
Intra Cos: 0.6449047923088074
Inter Cos: 0.1725880354642868
Norm Quadratic Average: 38.1445426940918
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.8019490838050842
Inter Cos: 0.24951393902301788
Norm Quadratic Average: 20.304121017456055
Nearest Class Center Accuracy: 0.9745

