Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_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: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09388834238052368
Inter Cos: 0.0988580510020256
Norm Quadratic Average: 3.981348991394043
Nearest Class Center Accuracy: 0.8601833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1550084948539734
Inter Cos: 0.11415284126996994
Norm Quadratic Average: 2.301971912384033
Nearest Class Center Accuracy: 0.9168666666666667

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17610548436641693
Inter Cos: 0.11201900243759155
Norm Quadratic Average: 1.7248728275299072
Nearest Class Center Accuracy: 0.94965

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2542110085487366
Inter Cos: 0.08375950157642365
Norm Quadratic Average: 1.260328769683838
Nearest Class Center Accuracy: 0.9893166666666666

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4684341549873352
Inter Cos: 0.10255568474531174
Norm Quadratic Average: 0.9441037178039551
Nearest Class Center Accuracy: 0.99865

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6872608661651611
Inter Cos: 0.06778007745742798
Norm Quadratic Average: 0.7930424213409424
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9543403387069702
Inter Cos: 0.032393958419561386
Norm Quadratic Average: 1.0261609554290771
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.100281000137329
Linear Weight Rank: 4028
Intra Cos: 0.9951457977294922
Inter Cos: -0.008810224011540413
Norm Quadratic Average: 25.825057983398438
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.47446346282959
Linear Weight Rank: 3638
Intra Cos: 0.9969642758369446
Inter Cos: 0.020144391804933548
Norm Quadratic Average: 18.61937141418457
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.297948122024536
Linear Weight Rank: 9
Intra Cos: 0.9974053502082825
Inter Cos: 0.03386002033948898
Norm Quadratic Average: 13.557770729064941
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9981912970542908
Inter Cos: 0.0742424875497818
Norm Quadratic Average: 10.521039962768555
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.017106325839832424
Accuracy: 0.9955
NC1 Within Class Collapse: 0.11247382313013077
NC2 Equinorm: Features: 0.016477975994348526, Weights: 0.006269274279475212
NC2 Equiangle: Features: 0.06932663387722439, Weights: 0.03505344655778673
NC3 Self-Duality: 0.013177604414522648
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
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: 0.10273852199316025
Inter Cos: 0.09979937970638275
Norm Quadratic Average: 3.957948923110962
Nearest Class Center Accuracy: 0.8729

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1639614850282669
Inter Cos: 0.11335570365190506
Norm Quadratic Average: 2.289482355117798
Nearest Class Center Accuracy: 0.9245

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18778738379478455
Inter Cos: 0.11029825359582901
Norm Quadratic Average: 1.7165238857269287
Nearest Class Center Accuracy: 0.9537

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2664845585823059
Inter Cos: 0.09242778271436691
Norm Quadratic Average: 1.2550570964813232
Nearest Class Center Accuracy: 0.9855

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48052507638931274
Inter Cos: 0.1046239361166954
Norm Quadratic Average: 0.9415720105171204
Nearest Class Center Accuracy: 0.9924

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6868593096733093
Inter Cos: 0.06794757395982742
Norm Quadratic Average: 0.7916672825813293
Nearest Class Center Accuracy: 0.9946

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9453119039535522
Inter Cos: 0.03754512220621109
Norm Quadratic Average: 1.0210200548171997
Nearest Class Center Accuracy: 0.9954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.100281000137329
Linear Weight Rank: 4028
Intra Cos: 0.9758790731430054
Inter Cos: 0.0011085602454841137
Norm Quadratic Average: 25.6599178314209
Nearest Class Center Accuracy: 0.9954

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.47446346282959
Linear Weight Rank: 3638
Intra Cos: 0.9780341982841492
Inter Cos: 0.030704153701663017
Norm Quadratic Average: 18.49872398376465
Nearest Class Center Accuracy: 0.9954

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.297948122024536
Linear Weight Rank: 9
Intra Cos: 0.9786725044250488
Inter Cos: 0.04456493631005287
Norm Quadratic Average: 13.470694541931152
Nearest Class Center Accuracy: 0.9954

Output Layer:
Intra Cos: 0.9799514412879944
Inter Cos: 0.08508053421974182
Norm Quadratic Average: 10.454629898071289
Nearest Class Center Accuracy: 0.9954

