Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_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: 0.11311887949705124
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: 0.10562729090452194
Inter Cos: 0.12616512179374695
Norm Quadratic Average: 87.90743255615234
Nearest Class Center Accuracy: 0.83125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15651321411132812
Inter Cos: 0.14842674136161804
Norm Quadratic Average: 54.67182922363281
Nearest Class Center Accuracy: 0.85325

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15148356556892395
Inter Cos: 0.14180755615234375
Norm Quadratic Average: 54.98063278198242
Nearest Class Center Accuracy: 0.866125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16940464079380035
Inter Cos: 0.12418205291032791
Norm Quadratic Average: 34.16960525512695
Nearest Class Center Accuracy: 0.903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17465800046920776
Inter Cos: 0.11191828548908234
Norm Quadratic Average: 35.8243293762207
Nearest Class Center Accuracy: 0.93

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20646052062511444
Inter Cos: 0.10314197093248367
Norm Quadratic Average: 24.21019172668457
Nearest Class Center Accuracy: 0.9685

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2843521237373352
Inter Cos: 0.11239314079284668
Norm Quadratic Average: 18.74233055114746
Nearest Class Center Accuracy: 0.994625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.04492950439453
Linear Weight Rank: 4031
Intra Cos: 0.47737738490104675
Inter Cos: 0.10801829397678375
Norm Quadratic Average: 116.11703491210938
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.62392044067383
Linear Weight Rank: 3671
Intra Cos: 0.6240781545639038
Inter Cos: 0.14492525160312653
Norm Quadratic Average: 61.92831039428711
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2343854904174805
Linear Weight Rank: 10
Intra Cos: 0.7504527568817139
Inter Cos: 0.18455255031585693
Norm Quadratic Average: 39.16049575805664
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9138135313987732
Inter Cos: 0.25725701451301575
Norm Quadratic Average: 20.788972854614258
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09779472035169602
Accuracy: 0.9755
NC1 Within Class Collapse: 1.6878783702850342
NC2 Equinorm: Features: 0.05405513197183609, Weights: 0.010416573844850063
NC2 Equiangle: Features: 0.19554854498969185, Weights: 0.086740509668986
NC3 Self-Duality: 0.6279952526092529
NC4 NCC Mismatch: 0.010000000000000009

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.13229374587535858
Inter Cos: 0.13847443461418152
Norm Quadratic Average: 86.775634765625
Nearest Class Center Accuracy: 0.8265

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16185475885868073
Inter Cos: 0.17134274542331696
Norm Quadratic Average: 54.388404846191406
Nearest Class Center Accuracy: 0.8505

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15667520463466644
Inter Cos: 0.16412287950515747
Norm Quadratic Average: 54.69194030761719
Nearest Class Center Accuracy: 0.867

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15886078774929047
Inter Cos: 0.1464858204126358
Norm Quadratic Average: 34.167640686035156
Nearest Class Center Accuracy: 0.9045

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1630353331565857
Inter Cos: 0.13503724336624146
Norm Quadratic Average: 35.853546142578125
Nearest Class Center Accuracy: 0.918

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18765421211719513
Inter Cos: 0.10127297043800354
Norm Quadratic Average: 24.191604614257812
Nearest Class Center Accuracy: 0.944

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.252023309469223
Inter Cos: 0.10879819095134735
Norm Quadratic Average: 18.599777221679688
Nearest Class Center Accuracy: 0.9645

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.04492950439453
Linear Weight Rank: 4031
Intra Cos: 0.40294840931892395
Inter Cos: 0.13506361842155457
Norm Quadratic Average: 113.55382537841797
Nearest Class Center Accuracy: 0.975

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.62392044067383
Linear Weight Rank: 3671
Intra Cos: 0.5322640538215637
Inter Cos: 0.15585558116436005
Norm Quadratic Average: 60.19935989379883
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2343854904174805
Linear Weight Rank: 10
Intra Cos: 0.6478549838066101
Inter Cos: 0.1927381306886673
Norm Quadratic Average: 37.88310623168945
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.8042088150978088
Inter Cos: 0.2679327130317688
Norm Quadratic Average: 19.98711585998535
Nearest Class Center Accuracy: 0.9715

