Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_265358_test_samples_None_train_samples_None_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: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06024523079395294
Inter Cos: 0.07874279469251633
Norm Quadratic Average: 2.4074888229370117
Nearest Class Center Accuracy: 0.8079333333333333

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10587369650602341
Inter Cos: 0.10225922614336014
Norm Quadratic Average: 1.3316607475280762
Nearest Class Center Accuracy: 0.87155

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10437803715467453
Inter Cos: 0.0977131724357605
Norm Quadratic Average: 1.052944540977478
Nearest Class Center Accuracy: 0.8774833333333333

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17423279583454132
Inter Cos: 0.11956854909658432
Norm Quadratic Average: 0.653180718421936
Nearest Class Center Accuracy: 0.9342833333333334

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23699773848056793
Inter Cos: 0.13987265527248383
Norm Quadratic Average: 0.46924856305122375
Nearest Class Center Accuracy: 0.96075

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.319413959980011
Inter Cos: 0.14686405658721924
Norm Quadratic Average: 0.38312506675720215
Nearest Class Center Accuracy: 0.9726666666666667

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3643428385257721
Inter Cos: 0.1583545058965683
Norm Quadratic Average: 0.3342091143131256
Nearest Class Center Accuracy: 0.9760666666666666

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4237551689147949
Inter Cos: 0.15501587092876434
Norm Quadratic Average: 0.2083483636379242
Nearest Class Center Accuracy: 0.9922666666666666

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6332564353942871
Inter Cos: 0.22085407376289368
Norm Quadratic Average: 0.13699212670326233
Nearest Class Center Accuracy: 0.9977333333333334

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7940415740013123
Inter Cos: 0.26685985922813416
Norm Quadratic Average: 0.12093903869390488
Nearest Class Center Accuracy: 0.9995

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8467379808425903
Inter Cos: 0.19012969732284546
Norm Quadratic Average: 0.11797536909580231
Nearest Class Center Accuracy: 0.9999166666666667

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9133944511413574
Inter Cos: 0.16125726699829102
Norm Quadratic Average: 0.11400320380926132
Nearest Class Center Accuracy: 0.99995

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9868788123130798
Inter Cos: 0.19890820980072021
Norm Quadratic Average: 0.15616725385189056
Nearest Class Center Accuracy: 0.99995

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9954432845115662
Inter Cos: 0.1251792013645172
Norm Quadratic Average: 0.4068267345428467
Nearest Class Center Accuracy: 0.99995

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.998155951499939
Inter Cos: 0.18414317071437836
Norm Quadratic Average: 0.9871254563331604
Nearest Class Center Accuracy: 0.99995

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.0326428413391113
Linear Weight Rank: 8
Intra Cos: 0.9989947080612183
Inter Cos: 0.2950945794582367
Norm Quadratic Average: 23.411087036132812
Nearest Class Center Accuracy: 0.99995

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.033912181854248
Linear Weight Rank: 1472
Intra Cos: 0.9991027116775513
Inter Cos: 0.2612460255622864
Norm Quadratic Average: 16.594932556152344
Nearest Class Center Accuracy: 0.99995

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.034846067428589
Linear Weight Rank: 8
Intra Cos: 0.9991060495376587
Inter Cos: 0.20611685514450073
Norm Quadratic Average: 12.064546585083008
Nearest Class Center Accuracy: 0.99995

Output Layer:
Intra Cos: 0.9991791248321533
Inter Cos: 0.2416384071111679
Norm Quadratic Average: 9.441658973693848
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.020398989325761795
Accuracy: 0.9954
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.024610385298728943, Weights: 0.007199566345661879
NC2 Equiangle: Features: 0.1714225133260091, Weights: 0.16398552788628473
NC3 Self-Duality: 0.034140899777412415
NC4 NCC Mismatch: 0.00039999999999995595

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048853933811188
Norm Quadratic Average: 23.595195770263672
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06860477477312088
Inter Cos: 0.08147197961807251
Norm Quadratic Average: 2.3978543281555176
Nearest Class Center Accuracy: 0.8182

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11585327237844467
Inter Cos: 0.1038740873336792
Norm Quadratic Average: 1.3219444751739502
Nearest Class Center Accuracy: 0.8834

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11416282504796982
Inter Cos: 0.09967315196990967
Norm Quadratic Average: 1.0492160320281982
Nearest Class Center Accuracy: 0.8875

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18634408712387085
Inter Cos: 0.12695463001728058
Norm Quadratic Average: 0.6507330536842346
Nearest Class Center Accuracy: 0.9397

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.250872939825058
Inter Cos: 0.14600658416748047
Norm Quadratic Average: 0.4685406982898712
Nearest Class Center Accuracy: 0.9612

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33435720205307007
Inter Cos: 0.15921619534492493
Norm Quadratic Average: 0.38268840312957764
Nearest Class Center Accuracy: 0.9725

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37864235043525696
Inter Cos: 0.1725330799818039
Norm Quadratic Average: 0.3337197005748749
Nearest Class Center Accuracy: 0.9762

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4360491931438446
Inter Cos: 0.1630886048078537
Norm Quadratic Average: 0.2080259919166565
Nearest Class Center Accuracy: 0.9889

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6446945071220398
Inter Cos: 0.23272836208343506
Norm Quadratic Average: 0.1370408535003662
Nearest Class Center Accuracy: 0.9933

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8037018775939941
Inter Cos: 0.2749348282814026
Norm Quadratic Average: 0.12111444771289825
Nearest Class Center Accuracy: 0.9937

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8521522283554077
Inter Cos: 0.20383688807487488
Norm Quadratic Average: 0.11791541427373886
Nearest Class Center Accuracy: 0.9947

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9098243117332458
Inter Cos: 0.15456052124500275
Norm Quadratic Average: 0.11371005326509476
Nearest Class Center Accuracy: 0.9946

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9643142223358154
Inter Cos: 0.1970999836921692
Norm Quadratic Average: 0.15560786426067352
Nearest Class Center Accuracy: 0.9956

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9768012166023254
Inter Cos: 0.13170704245567322
Norm Quadratic Average: 0.40556755661964417
Nearest Class Center Accuracy: 0.9954

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9786443114280701
Inter Cos: 0.18105977773666382
Norm Quadratic Average: 0.9846506714820862
Nearest Class Center Accuracy: 0.9954

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.0326428413391113
Linear Weight Rank: 8
Intra Cos: 0.9813909530639648
Inter Cos: 0.2971371114253998
Norm Quadratic Average: 23.34265899658203
Nearest Class Center Accuracy: 0.9954

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.033912181854248
Linear Weight Rank: 1472
Intra Cos: 0.9820863604545593
Inter Cos: 0.2637036144733429
Norm Quadratic Average: 16.54513931274414
Nearest Class Center Accuracy: 0.9955

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.034846067428589
Linear Weight Rank: 8
Intra Cos: 0.9824517369270325
Inter Cos: 0.20924435555934906
Norm Quadratic Average: 12.02772331237793
Nearest Class Center Accuracy: 0.9954

Output Layer:
Intra Cos: 0.9831200838088989
Inter Cos: 0.24008050560951233
Norm Quadratic Average: 9.41254711151123
Nearest Class Center Accuracy: 0.9951

