Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
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: 0.10530997067689896
Inter Cos: 0.12787970900535583
Norm Quadratic Average: 35.35773849487305
Nearest Class Center Accuracy: 0.829

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14629393815994263
Inter Cos: 0.14098966121673584
Norm Quadratic Average: 22.120019912719727
Nearest Class Center Accuracy: 0.85175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15492665767669678
Inter Cos: 0.13247396051883698
Norm Quadratic Average: 21.432287216186523
Nearest Class Center Accuracy: 0.87575

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19652821123600006
Inter Cos: 0.10678677260875702
Norm Quadratic Average: 13.221446990966797
Nearest Class Center Accuracy: 0.92975

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21816623210906982
Inter Cos: 0.1045001745223999
Norm Quadratic Average: 13.492593765258789
Nearest Class Center Accuracy: 0.96275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2939431071281433
Inter Cos: 0.10249754041433334
Norm Quadratic Average: 9.157445907592773
Nearest Class Center Accuracy: 0.9955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5403839349746704
Inter Cos: 0.09159566462039948
Norm Quadratic Average: 7.333039283752441
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.7998046875
Linear Weight Rank: 4031
Intra Cos: 0.8512413501739502
Inter Cos: 0.09311672300100327
Norm Quadratic Average: 69.10772705078125
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.7257080078125
Linear Weight Rank: 3670
Intra Cos: 0.939006507396698
Inter Cos: 0.11414626985788345
Norm Quadratic Average: 31.864501953125
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.549849271774292
Linear Weight Rank: 10
Intra Cos: 0.9561066627502441
Inter Cos: 0.15104123950004578
Norm Quadratic Average: 17.723331451416016
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9663842916488647
Inter Cos: 0.2751236855983734
Norm Quadratic Average: 9.590370178222656
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07003851366043091
Accuracy: 0.982
NC1 Within Class Collapse: 0.9920378923416138
NC2 Equinorm: Features: 0.05327784642577171, Weights: 0.017185518518090248
NC2 Equiangle: Features: 0.18643701341417102, Weights: 0.09034678141276041
NC3 Self-Duality: 0.16881108283996582
NC4 NCC Mismatch: 0.0020000000000000018

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: 0.13039477169513702
Inter Cos: 0.1390758603811264
Norm Quadratic Average: 34.738189697265625
Nearest Class Center Accuracy: 0.824

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1609710156917572
Inter Cos: 0.1677423119544983
Norm Quadratic Average: 21.865055084228516
Nearest Class Center Accuracy: 0.846

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15718521177768707
Inter Cos: 0.15255320072174072
Norm Quadratic Average: 21.22647476196289
Nearest Class Center Accuracy: 0.868

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18955016136169434
Inter Cos: 0.13048039376735687
Norm Quadratic Average: 13.15136432647705
Nearest Class Center Accuracy: 0.919

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2126612365245819
Inter Cos: 0.12815162539482117
Norm Quadratic Average: 13.457292556762695
Nearest Class Center Accuracy: 0.9455

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2829848527908325
Inter Cos: 0.10985676944255829
Norm Quadratic Average: 9.120979309082031
Nearest Class Center Accuracy: 0.974

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47504809498786926
Inter Cos: 0.11674967408180237
Norm Quadratic Average: 7.226527690887451
Nearest Class Center Accuracy: 0.9825

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.7998046875
Linear Weight Rank: 4031
Intra Cos: 0.7400758862495422
Inter Cos: 0.12478179484605789
Norm Quadratic Average: 66.79808807373047
Nearest Class Center Accuracy: 0.983

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.7257080078125
Linear Weight Rank: 3670
Intra Cos: 0.8353180885314941
Inter Cos: 0.14678466320037842
Norm Quadratic Average: 30.707622528076172
Nearest Class Center Accuracy: 0.983

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.549849271774292
Linear Weight Rank: 10
Intra Cos: 0.8565117120742798
Inter Cos: 0.1537075638771057
Norm Quadratic Average: 17.103065490722656
Nearest Class Center Accuracy: 0.983

Output Layer:
Intra Cos: 0.8723490834236145
Inter Cos: 0.25947126746177673
Norm Quadratic Average: 9.252782821655273
Nearest Class Center Accuracy: 0.9825

