Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_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: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12555694580078125
Inter Cos: 0.15690600872039795
Norm Quadratic Average: 36.698890686035156
Nearest Class Center Accuracy: 0.7998833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1534329205751419
Inter Cos: 0.1926201730966568
Norm Quadratic Average: 41.164512634277344
Nearest Class Center Accuracy: 0.77065

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18818563222885132
Inter Cos: 0.22983698546886444
Norm Quadratic Average: 51.460384368896484
Nearest Class Center Accuracy: 0.7898333333333334

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16638445854187012
Inter Cos: 0.24239596724510193
Norm Quadratic Average: 33.199405670166016
Nearest Class Center Accuracy: 0.8163

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2113211303949356
Inter Cos: 0.30094897747039795
Norm Quadratic Average: 21.265947341918945
Nearest Class Center Accuracy: 0.8642666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38160473108291626
Inter Cos: 0.4255116581916809
Norm Quadratic Average: 11.726752281188965
Nearest Class Center Accuracy: 0.9067

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5658433437347412
Inter Cos: 0.4638703465461731
Norm Quadratic Average: 10.972716331481934
Nearest Class Center Accuracy: 0.9493333333333334

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.6544642448425293
Linear Weight Rank: 7
Intra Cos: 0.6535913348197937
Inter Cos: 0.4007943570613861
Norm Quadratic Average: 47.809043884277344
Nearest Class Center Accuracy: 0.97255

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.6571044921875
Linear Weight Rank: 2788
Intra Cos: 0.672857403755188
Inter Cos: 0.410208135843277
Norm Quadratic Average: 32.0579719543457
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.6516228914260864
Linear Weight Rank: 9
Intra Cos: 0.6995582580566406
Inter Cos: 0.3633372485637665
Norm Quadratic Average: 20.324481964111328
Nearest Class Center Accuracy: 0.9775166666666667

Output Layer:
Intra Cos: 0.7194576263427734
Inter Cos: 0.40201061964035034
Norm Quadratic Average: 14.347164154052734
Nearest Class Center Accuracy: 0.9774833333333334

Test Set:
Average Loss: 0.06138446587622166
Accuracy: 0.9825
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.17349861562252045, Weights: 0.04947522655129433
NC2 Equiangle: Features: 0.29417987399631074, Weights: 0.21584883795844184
NC3 Self-Duality: 0.11487741023302078
NC4 NCC Mismatch: 0.01419999999999999

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13905848562717438
Inter Cos: 0.17187732458114624
Norm Quadratic Average: 36.78439712524414
Nearest Class Center Accuracy: 0.8174

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17002129554748535
Inter Cos: 0.21264880895614624
Norm Quadratic Average: 41.165287017822266
Nearest Class Center Accuracy: 0.7894

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20242367684841156
Inter Cos: 0.2518119215965271
Norm Quadratic Average: 51.443363189697266
Nearest Class Center Accuracy: 0.809

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17612294852733612
Inter Cos: 0.2457052618265152
Norm Quadratic Average: 33.16181945800781
Nearest Class Center Accuracy: 0.8353

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22268536686897278
Inter Cos: 0.2973993718624115
Norm Quadratic Average: 21.29050636291504
Nearest Class Center Accuracy: 0.8787

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40172818303108215
Inter Cos: 0.4256524443626404
Norm Quadratic Average: 11.776213645935059
Nearest Class Center Accuracy: 0.916

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5739150047302246
Inter Cos: 0.4559022784233093
Norm Quadratic Average: 11.065570831298828
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.6544642448425293
Linear Weight Rank: 7
Intra Cos: 0.6592655777931213
Inter Cos: 0.3863607347011566
Norm Quadratic Average: 48.32946014404297
Nearest Class Center Accuracy: 0.9713

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.6571044921875
Linear Weight Rank: 2788
Intra Cos: 0.6711344718933105
Inter Cos: 0.4249103367328644
Norm Quadratic Average: 32.48541259765625
Nearest Class Center Accuracy: 0.9765

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.6516228914260864
Linear Weight Rank: 9
Intra Cos: 0.6896883249282837
Inter Cos: 0.37251678109169006
Norm Quadratic Average: 20.61997413635254
Nearest Class Center Accuracy: 0.9764

Output Layer:
Intra Cos: 0.7013067007064819
Inter Cos: 0.4166550040245056
Norm Quadratic Average: 14.57266902923584
Nearest Class Center Accuracy: 0.977

