Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.01.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12096305936574936
Inter Cos: 0.14331257343292236
Norm Quadratic Average: 42.1811408996582
Nearest Class Center Accuracy: 0.811625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1621791422367096
Inter Cos: 0.17833642661571503
Norm Quadratic Average: 46.343116760253906
Nearest Class Center Accuracy: 0.78475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17581932246685028
Inter Cos: 0.1938599944114685
Norm Quadratic Average: 58.984092712402344
Nearest Class Center Accuracy: 0.785375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18329472839832306
Inter Cos: 0.19624537229537964
Norm Quadratic Average: 35.6798210144043
Nearest Class Center Accuracy: 0.82375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21448548138141632
Inter Cos: 0.2247972935438156
Norm Quadratic Average: 27.17323875427246
Nearest Class Center Accuracy: 0.87575

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3145545423030853
Inter Cos: 0.21889737248420715
Norm Quadratic Average: 13.413215637207031
Nearest Class Center Accuracy: 0.92875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46657469868659973
Inter Cos: 0.26647019386291504
Norm Quadratic Average: 8.955371856689453
Nearest Class Center Accuracy: 0.967625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74653244018555
Linear Weight Rank: 4031
Intra Cos: 0.6676914691925049
Inter Cos: 0.2967684864997864
Norm Quadratic Average: 39.835792541503906
Nearest Class Center Accuracy: 0.992375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.401927947998047
Linear Weight Rank: 3670
Intra Cos: 0.7522976398468018
Inter Cos: 0.2849765121936798
Norm Quadratic Average: 27.202295303344727
Nearest Class Center Accuracy: 0.996625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.149240016937256
Linear Weight Rank: 10
Intra Cos: 0.7782827019691467
Inter Cos: 0.2652490437030792
Norm Quadratic Average: 21.589784622192383
Nearest Class Center Accuracy: 0.99625

Output Layer:
Intra Cos: 0.8093069195747375
Inter Cos: 0.3011852204799652
Norm Quadratic Average: 16.53182029724121
Nearest Class Center Accuracy: 0.995

Test Set:
Average Loss: 0.07048952931165695
Accuracy: 0.975
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.11098984628915787, Weights: 0.02753991074860096
NC2 Equiangle: Features: 0.27290450202094185, Weights: 0.1260819329155816
NC3 Self-Duality: 0.3140527904033661
NC4 NCC Mismatch: 0.01200000000000001

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: 0.13738365471363068
Inter Cos: 0.15766765177249908
Norm Quadratic Average: 40.835044860839844
Nearest Class Center Accuracy: 0.8075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16717688739299774
Inter Cos: 0.20739097893238068
Norm Quadratic Average: 44.89387893676758
Nearest Class Center Accuracy: 0.783

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17763741314411163
Inter Cos: 0.23531796038150787
Norm Quadratic Average: 57.021724700927734
Nearest Class Center Accuracy: 0.7875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16419129073619843
Inter Cos: 0.23631364107131958
Norm Quadratic Average: 34.57775115966797
Nearest Class Center Accuracy: 0.818

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19277361035346985
Inter Cos: 0.26219114661216736
Norm Quadratic Average: 26.400678634643555
Nearest Class Center Accuracy: 0.862

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27896228432655334
Inter Cos: 0.2551968991756439
Norm Quadratic Average: 12.992083549499512
Nearest Class Center Accuracy: 0.9255

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4157474637031555
Inter Cos: 0.2944234013557434
Norm Quadratic Average: 8.634504318237305
Nearest Class Center Accuracy: 0.9515

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74653244018555
Linear Weight Rank: 4031
Intra Cos: 0.6017347574234009
Inter Cos: 0.32389888167381287
Norm Quadratic Average: 38.28943634033203
Nearest Class Center Accuracy: 0.9655

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.401927947998047
Linear Weight Rank: 3670
Intra Cos: 0.6844772100448608
Inter Cos: 0.31143081188201904
Norm Quadratic Average: 26.12074851989746
Nearest Class Center Accuracy: 0.971

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.149240016937256
Linear Weight Rank: 10
Intra Cos: 0.708026647567749
Inter Cos: 0.2818589210510254
Norm Quadratic Average: 20.7239933013916
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7331205606460571
Inter Cos: 0.2830394208431244
Norm Quadratic Average: 15.837007522583008
Nearest Class Center Accuracy: 0.973

