Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_846264_test_samples_None_train_samples_None_weight_decay_0.005.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: 0.10967151820659637
Norm Quadratic Average: 23.567686080932617
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06012536957859993
Inter Cos: 0.07720869779586792
Norm Quadratic Average: 2.8383378982543945
Nearest Class Center Accuracy: 0.8109166666666666

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10244590044021606
Inter Cos: 0.09663300961256027
Norm Quadratic Average: 1.6669774055480957
Nearest Class Center Accuracy: 0.8734

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09901539236307144
Inter Cos: 0.09036935865879059
Norm Quadratic Average: 1.380863070487976
Nearest Class Center Accuracy: 0.88095

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17744114995002747
Inter Cos: 0.1134740486741066
Norm Quadratic Average: 0.9448097944259644
Nearest Class Center Accuracy: 0.9371833333333334

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2349356710910797
Inter Cos: 0.12586432695388794
Norm Quadratic Average: 0.7080089449882507
Nearest Class Center Accuracy: 0.96215

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3074723780155182
Inter Cos: 0.1379804015159607
Norm Quadratic Average: 0.5861450433731079
Nearest Class Center Accuracy: 0.9743333333333334

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3453556001186371
Inter Cos: 0.1387070268392563
Norm Quadratic Average: 0.4980432987213135
Nearest Class Center Accuracy: 0.9772666666666666

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42512649297714233
Inter Cos: 0.16263428330421448
Norm Quadratic Average: 0.32527443766593933
Nearest Class Center Accuracy: 0.9929166666666667

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6743717789649963
Inter Cos: 0.2350524216890335
Norm Quadratic Average: 0.21644288301467896
Nearest Class Center Accuracy: 0.9985166666666667

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8178778290748596
Inter Cos: 0.2539446949958801
Norm Quadratic Average: 0.21019402146339417
Nearest Class Center Accuracy: 0.9992666666666666

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8623893857002258
Inter Cos: 0.18174335360527039
Norm Quadratic Average: 0.21276302635669708
Nearest Class Center Accuracy: 0.9999166666666667

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9146928191184998
Inter Cos: 0.1219407320022583
Norm Quadratic Average: 0.24093210697174072
Nearest Class Center Accuracy: 0.9999833333333333

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9879118800163269
Inter Cos: 0.06301520019769669
Norm Quadratic Average: 0.2893044054508209
Nearest Class Center Accuracy: 0.9999833333333333

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9973711371421814
Inter Cos: 0.08557306975126266
Norm Quadratic Average: 0.5355697870254517
Nearest Class Center Accuracy: 0.9999833333333333

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9986758232116699
Inter Cos: 0.11318844556808472
Norm Quadratic Average: 1.0999372005462646
Nearest Class Center Accuracy: 0.9999833333333333

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.13417911529541
Linear Weight Rank: 10
Intra Cos: 0.9992841482162476
Inter Cos: 0.194422647356987
Norm Quadratic Average: 24.6955623626709
Nearest Class Center Accuracy: 0.9999833333333333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.13663387298584
Linear Weight Rank: 1529
Intra Cos: 0.9994072914123535
Inter Cos: 0.21486899256706238
Norm Quadratic Average: 17.242385864257812
Nearest Class Center Accuracy: 0.9999833333333333

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.136704921722412
Linear Weight Rank: 9
Intra Cos: 0.9994232654571533
Inter Cos: 0.18861189484596252
Norm Quadratic Average: 12.31859016418457
Nearest Class Center Accuracy: 0.9999833333333333

Output Layer:
Intra Cos: 0.9995220303535461
Inter Cos: 0.116030752658844
Norm Quadratic Average: 9.286462783813477
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.018743926553614437
Accuracy: 0.996
NC1 Within Class Collapse: 0.08376509696245193
NC2 Equinorm: Features: 0.016919206827878952, Weights: 0.006003889720886946
NC2 Equiangle: Features: 0.12083986070421007, Weights: 0.08393193350897896
NC3 Self-Duality: 0.03542302921414375
NC4 NCC Mismatch: 0.0

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.59519386291504
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06850119680166245
Inter Cos: 0.07955019176006317
Norm Quadratic Average: 2.828272581100464
Nearest Class Center Accuracy: 0.8202

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11247612535953522
Inter Cos: 0.09832628816366196
Norm Quadratic Average: 1.6563608646392822
Nearest Class Center Accuracy: 0.8849

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10910382121801376
Inter Cos: 0.09218409657478333
Norm Quadratic Average: 1.3775689601898193
Nearest Class Center Accuracy: 0.8872

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18917368352413177
Inter Cos: 0.1242622584104538
Norm Quadratic Average: 0.9408014416694641
Nearest Class Center Accuracy: 0.9435

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25058239698410034
Inter Cos: 0.1393895298242569
Norm Quadratic Average: 0.7057997584342957
Nearest Class Center Accuracy: 0.9642

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3236737847328186
Inter Cos: 0.15250059962272644
Norm Quadratic Average: 0.5849136114120483
Nearest Class Center Accuracy: 0.9737

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3618152141571045
Inter Cos: 0.152368426322937
Norm Quadratic Average: 0.4966792166233063
Nearest Class Center Accuracy: 0.9772

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43922317028045654
Inter Cos: 0.17897117137908936
Norm Quadratic Average: 0.32425031065940857
Nearest Class Center Accuracy: 0.9885

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.685044527053833
Inter Cos: 0.2479088306427002
Norm Quadratic Average: 0.21641609072685242
Nearest Class Center Accuracy: 0.9935

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8223994374275208
Inter Cos: 0.2627575993537903
Norm Quadratic Average: 0.21048764884471893
Nearest Class Center Accuracy: 0.9949

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8650075793266296
Inter Cos: 0.19101202487945557
Norm Quadratic Average: 0.21272097527980804
Nearest Class Center Accuracy: 0.995

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9125621318817139
Inter Cos: 0.11784924566745758
Norm Quadratic Average: 0.24067538976669312
Nearest Class Center Accuracy: 0.9957

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9736878871917725
Inter Cos: 0.07102014124393463
Norm Quadratic Average: 0.28854045271873474
Nearest Class Center Accuracy: 0.9958

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9774913787841797
Inter Cos: 0.0925910472869873
Norm Quadratic Average: 0.5338854193687439
Nearest Class Center Accuracy: 0.9962

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9799090623855591
Inter Cos: 0.11982715874910355
Norm Quadratic Average: 1.0966211557388306
Nearest Class Center Accuracy: 0.9961

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.13417911529541
Linear Weight Rank: 10
Intra Cos: 0.9811514616012573
Inter Cos: 0.19954335689544678
Norm Quadratic Average: 24.627796173095703
Nearest Class Center Accuracy: 0.9961

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.13663387298584
Linear Weight Rank: 1529
Intra Cos: 0.982326090335846
Inter Cos: 0.21144035458564758
Norm Quadratic Average: 17.191776275634766
Nearest Class Center Accuracy: 0.996

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.136704921722412
Linear Weight Rank: 9
Intra Cos: 0.9826804399490356
Inter Cos: 0.19178037345409393
Norm Quadratic Average: 12.280497550964355
Nearest Class Center Accuracy: 0.996

Output Layer:
Intra Cos: 0.9838529825210571
Inter Cos: 0.1255180537700653
Norm Quadratic Average: 9.253888130187988
Nearest Class Center Accuracy: 0.996

