Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.007.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: 0.11311887204647064
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: 0.11452582478523254
Inter Cos: 0.1340303272008896
Norm Quadratic Average: 41.10935974121094
Nearest Class Center Accuracy: 0.8185

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15806491672992706
Inter Cos: 0.17003455758094788
Norm Quadratic Average: 41.11836242675781
Nearest Class Center Accuracy: 0.804

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17853590846061707
Inter Cos: 0.1902994066476822
Norm Quadratic Average: 50.66718292236328
Nearest Class Center Accuracy: 0.811875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19802458584308624
Inter Cos: 0.19309572875499725
Norm Quadratic Average: 31.500768661499023
Nearest Class Center Accuracy: 0.842625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.229958176612854
Inter Cos: 0.2170936018228531
Norm Quadratic Average: 25.590229034423828
Nearest Class Center Accuracy: 0.89475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3135349154472351
Inter Cos: 0.20397476851940155
Norm Quadratic Average: 13.72161865234375
Nearest Class Center Accuracy: 0.94275

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46017754077911377
Inter Cos: 0.2616068422794342
Norm Quadratic Average: 9.600025177001953
Nearest Class Center Accuracy: 0.978875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46883392333984
Linear Weight Rank: 4031
Intra Cos: 0.664974570274353
Inter Cos: 0.2909754812717438
Norm Quadratic Average: 43.2607421875
Nearest Class Center Accuracy: 0.99625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.32177734375
Linear Weight Rank: 3671
Intra Cos: 0.7407894134521484
Inter Cos: 0.2887049615383148
Norm Quadratic Average: 29.38216781616211
Nearest Class Center Accuracy: 0.9985

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2143983840942383
Linear Weight Rank: 10
Intra Cos: 0.7594228386878967
Inter Cos: 0.27478960156440735
Norm Quadratic Average: 23.371049880981445
Nearest Class Center Accuracy: 0.998625

Output Layer:
Intra Cos: 0.7723004817962646
Inter Cos: 0.3316756784915924
Norm Quadratic Average: 17.79331398010254
Nearest Class Center Accuracy: 0.998125

Test Set:
Average Loss: 0.07009645795822143
Accuracy: 0.978
NC1 Within Class Collapse: 2.1979663372039795
NC2 Equinorm: Features: 0.13308045268058777, Weights: 0.023706724867224693
NC2 Equiangle: Features: 0.268675782945421, Weights: 0.11847279866536459
NC3 Self-Duality: 0.373746782541275
NC4 NCC Mismatch: 0.013000000000000012

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: 0.13611210882663727
Inter Cos: 0.15285038948059082
Norm Quadratic Average: 40.21039962768555
Nearest Class Center Accuracy: 0.8105

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17290228605270386
Inter Cos: 0.2091710865497589
Norm Quadratic Average: 40.28740310668945
Nearest Class Center Accuracy: 0.8015

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18482929468154907
Inter Cos: 0.23022988438606262
Norm Quadratic Average: 49.596519470214844
Nearest Class Center Accuracy: 0.812

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18064472079277039
Inter Cos: 0.22716963291168213
Norm Quadratic Average: 30.815208435058594
Nearest Class Center Accuracy: 0.837

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2125871330499649
Inter Cos: 0.25012871623039246
Norm Quadratic Average: 25.098703384399414
Nearest Class Center Accuracy: 0.8835

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2900417149066925
Inter Cos: 0.21573206782341003
Norm Quadratic Average: 13.422249794006348
Nearest Class Center Accuracy: 0.9325

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41811424493789673
Inter Cos: 0.2542811632156372
Norm Quadratic Average: 9.36215877532959
Nearest Class Center Accuracy: 0.9575

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46883392333984
Linear Weight Rank: 4031
Intra Cos: 0.604179322719574
Inter Cos: 0.28605684638023376
Norm Quadratic Average: 41.99078369140625
Nearest Class Center Accuracy: 0.969

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.32177734375
Linear Weight Rank: 3671
Intra Cos: 0.6707885265350342
Inter Cos: 0.27268534898757935
Norm Quadratic Average: 28.495004653930664
Nearest Class Center Accuracy: 0.9735

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2143983840942383
Linear Weight Rank: 10
Intra Cos: 0.6836448907852173
Inter Cos: 0.2675032615661621
Norm Quadratic Average: 22.690425872802734
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.685357928276062
Inter Cos: 0.3475099802017212
Norm Quadratic Average: 17.266002655029297
Nearest Class Center Accuracy: 0.972

