Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.001.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11175180971622467
Inter Cos: 0.13579650223255157
Norm Quadratic Average: 45.3270149230957
Nearest Class Center Accuracy: 0.81775

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14777790009975433
Inter Cos: 0.1692287176847458
Norm Quadratic Average: 45.859806060791016
Nearest Class Center Accuracy: 0.801625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16101716458797455
Inter Cos: 0.18707749247550964
Norm Quadratic Average: 60.76408386230469
Nearest Class Center Accuracy: 0.80975

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19732092320919037
Inter Cos: 0.19207455217838287
Norm Quadratic Average: 38.377933502197266
Nearest Class Center Accuracy: 0.843875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2294294536113739
Inter Cos: 0.207575723528862
Norm Quadratic Average: 36.87246322631836
Nearest Class Center Accuracy: 0.88375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27862080931663513
Inter Cos: 0.18429283797740936
Norm Quadratic Average: 21.419084548950195
Nearest Class Center Accuracy: 0.928625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3981105089187622
Inter Cos: 0.21138793230056763
Norm Quadratic Average: 16.24224853515625
Nearest Class Center Accuracy: 0.972625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63322448730469
Linear Weight Rank: 4031
Intra Cos: 0.6237407922744751
Inter Cos: 0.23962989449501038
Norm Quadratic Average: 70.84117889404297
Nearest Class Center Accuracy: 0.998375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06365203857422
Linear Weight Rank: 3670
Intra Cos: 0.7281749844551086
Inter Cos: 0.2600800693035126
Norm Quadratic Average: 46.018592834472656
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.453167200088501
Linear Weight Rank: 10
Intra Cos: 0.7781713604927063
Inter Cos: 0.27069491147994995
Norm Quadratic Average: 36.118690490722656
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8180031776428223
Inter Cos: 0.3907758295536041
Norm Quadratic Average: 26.286602020263672
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.08084400555491447
Accuracy: 0.9815
NC1 Within Class Collapse: 1.7876371145248413
NC2 Equinorm: Features: 0.12191299349069595, Weights: 0.01372496783733368
NC2 Equiangle: Features: 0.24043621487087674, Weights: 0.09565554724799262
NC3 Self-Duality: 0.5302183032035828
NC4 NCC Mismatch: 0.01200000000000001

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: 0.13524553179740906
Inter Cos: 0.1509767323732376
Norm Quadratic Average: 44.17848587036133
Nearest Class Center Accuracy: 0.8125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17076650261878967
Inter Cos: 0.19850172102451324
Norm Quadratic Average: 44.75139236450195
Nearest Class Center Accuracy: 0.7955

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1818433403968811
Inter Cos: 0.22368597984313965
Norm Quadratic Average: 59.20840072631836
Nearest Class Center Accuracy: 0.811

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.175770103931427
Inter Cos: 0.22534537315368652
Norm Quadratic Average: 37.512821197509766
Nearest Class Center Accuracy: 0.842

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.197953462600708
Inter Cos: 0.24033059179782867
Norm Quadratic Average: 36.0406494140625
Nearest Class Center Accuracy: 0.875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24617083370685577
Inter Cos: 0.21123187243938446
Norm Quadratic Average: 20.933496475219727
Nearest Class Center Accuracy: 0.9235

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3505534529685974
Inter Cos: 0.2435186207294464
Norm Quadratic Average: 15.806328773498535
Nearest Class Center Accuracy: 0.9555

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63322448730469
Linear Weight Rank: 4031
Intra Cos: 0.555155336856842
Inter Cos: 0.27485841512680054
Norm Quadratic Average: 68.64160919189453
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06365203857422
Linear Weight Rank: 3670
Intra Cos: 0.6492780447006226
Inter Cos: 0.2811868190765381
Norm Quadratic Average: 44.4908447265625
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.453167200088501
Linear Weight Rank: 10
Intra Cos: 0.6924411654472351
Inter Cos: 0.3073294162750244
Norm Quadratic Average: 34.977970123291016
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7211652994155884
Inter Cos: 0.4230888783931732
Norm Quadratic Average: 25.43739128112793
Nearest Class Center Accuracy: 0.9705

