Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg19_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477277636528015
Norm Quadratic Average: 27.597183227539062
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019283460453152657
Inter Cos: 0.08463044464588165
Norm Quadratic Average: 37.98534393310547
Nearest Class Center Accuracy: 0.34758

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020640339702367783
Inter Cos: 0.07282666116952896
Norm Quadratic Average: 40.58576202392578
Nearest Class Center Accuracy: 0.4783

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023278167471289635
Inter Cos: 0.06470105797052383
Norm Quadratic Average: 54.71995162963867
Nearest Class Center Accuracy: 0.55524

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025285184383392334
Inter Cos: 0.06430482119321823
Norm Quadratic Average: 37.10506820678711
Nearest Class Center Accuracy: 0.61528

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029408665373921394
Inter Cos: 0.057096149772405624
Norm Quadratic Average: 33.0152587890625
Nearest Class Center Accuracy: 0.6607

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03547576069831848
Inter Cos: 0.0510944128036499
Norm Quadratic Average: 24.575101852416992
Nearest Class Center Accuracy: 0.69624

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03643867373466492
Inter Cos: 0.04130760207772255
Norm Quadratic Average: 17.564828872680664
Nearest Class Center Accuracy: 0.72772

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05752550810575485
Inter Cos: 0.06302701681852341
Norm Quadratic Average: 7.233308792114258
Nearest Class Center Accuracy: 0.80794

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13470827043056488
Inter Cos: 0.09903997927904129
Norm Quadratic Average: 4.2478766441345215
Nearest Class Center Accuracy: 0.86344

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2930048108100891
Inter Cos: 0.19168081879615784
Norm Quadratic Average: 2.8152503967285156
Nearest Class Center Accuracy: 0.93238

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43138808012008667
Inter Cos: 0.2524549663066864
Norm Quadratic Average: 2.3425772190093994
Nearest Class Center Accuracy: 0.97334

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6209419965744019
Inter Cos: 0.3104000687599182
Norm Quadratic Average: 1.600217580795288
Nearest Class Center Accuracy: 0.99142

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8313072323799133
Inter Cos: 0.2702590823173523
Norm Quadratic Average: 1.575940489768982
Nearest Class Center Accuracy: 0.99834

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8742443323135376
Inter Cos: 0.22822290658950806
Norm Quadratic Average: 1.8511103391647339
Nearest Class Center Accuracy: 0.9999

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8881813287734985
Inter Cos: 0.21342433989048004
Norm Quadratic Average: 2.166613817214966
Nearest Class Center Accuracy: 0.99998

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.31645393371582
Linear Weight Rank: 4031
Intra Cos: 0.9135614037513733
Inter Cos: 0.18346372246742249
Norm Quadratic Average: 14.67325210571289
Nearest Class Center Accuracy: 1.0

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.805445671081543
Linear Weight Rank: 3667
Intra Cos: 0.9196005463600159
Inter Cos: 0.18944227695465088
Norm Quadratic Average: 15.008957862854004
Nearest Class Center Accuracy: 1.0

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.1622087955474854
Linear Weight Rank: 10
Intra Cos: 0.9119731783866882
Inter Cos: 0.15802398324012756
Norm Quadratic Average: 15.769652366638184
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9088258743286133
Inter Cos: 0.24612180888652802
Norm Quadratic Average: 18.875471115112305
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.8417762014389039
Accuracy: 0.841
NC1 Within Class Collapse: 4.427484035491943
NC2 Equinorm: Features: 0.18214461207389832, Weights: 0.018948808312416077
NC2 Equiangle: Features: 0.2511589050292969, Weights: 0.15392864015367297
NC3 Self-Duality: 0.16226300597190857
NC4 NCC Mismatch: 0.03149999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526075407862663
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017766891047358513
Inter Cos: 0.08458951115608215
Norm Quadratic Average: 37.951168060302734
Nearest Class Center Accuracy: 0.3627

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0194274690002203
Inter Cos: 0.07369400560855865
Norm Quadratic Average: 40.55339813232422
Nearest Class Center Accuracy: 0.4958

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022154275327920914
Inter Cos: 0.06518888473510742
Norm Quadratic Average: 54.69718551635742
Nearest Class Center Accuracy: 0.5654

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023379892110824585
Inter Cos: 0.06504247337579727
Norm Quadratic Average: 37.11402130126953
Nearest Class Center Accuracy: 0.6198

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02712329477071762
Inter Cos: 0.05764266476035118
Norm Quadratic Average: 33.05002975463867
Nearest Class Center Accuracy: 0.6555

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032429635524749756
Inter Cos: 0.05190819501876831
Norm Quadratic Average: 24.598451614379883
Nearest Class Center Accuracy: 0.6815

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03281145542860031
Inter Cos: 0.04266342148184776
Norm Quadratic Average: 17.57204246520996
Nearest Class Center Accuracy: 0.6995

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.049084559082984924
Inter Cos: 0.06404674798250198
Norm Quadratic Average: 7.223628520965576
Nearest Class Center Accuracy: 0.7468

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11189810931682587
Inter Cos: 0.1020810604095459
Norm Quadratic Average: 4.22445821762085
Nearest Class Center Accuracy: 0.7738

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23068732023239136
Inter Cos: 0.18887928128242493
Norm Quadratic Average: 2.7876060009002686
Nearest Class Center Accuracy: 0.803

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31137606501579285
Inter Cos: 0.2523314952850342
Norm Quadratic Average: 2.307098627090454
Nearest Class Center Accuracy: 0.8198

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4211488664150238
Inter Cos: 0.3270370662212372
Norm Quadratic Average: 1.5630449056625366
Nearest Class Center Accuracy: 0.8278

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5293444991111755
Inter Cos: 0.3685426712036133
Norm Quadratic Average: 1.5151572227478027
Nearest Class Center Accuracy: 0.8316

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5219841003417969
Inter Cos: 0.3327842056751251
Norm Quadratic Average: 1.7663683891296387
Nearest Class Center Accuracy: 0.8332

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5076544880867004
Inter Cos: 0.3081420660018921
Norm Quadratic Average: 2.0599615573883057
Nearest Class Center Accuracy: 0.8342

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.31645393371582
Linear Weight Rank: 4031
Intra Cos: 0.5316322445869446
Inter Cos: 0.2822781801223755
Norm Quadratic Average: 13.925175666809082
Nearest Class Center Accuracy: 0.8335

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.805445671081543
Linear Weight Rank: 3667
Intra Cos: 0.5233517289161682
Inter Cos: 0.25983545184135437
Norm Quadratic Average: 14.261676788330078
Nearest Class Center Accuracy: 0.8352

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.1622087955474854
Linear Weight Rank: 10
Intra Cos: 0.5074461102485657
Inter Cos: 0.26605692505836487
Norm Quadratic Average: 15.061610221862793
Nearest Class Center Accuracy: 0.8391

Output Layer:
Intra Cos: 0.5010959506034851
Inter Cos: 0.32131680846214294
Norm Quadratic Average: 18.047195434570312
Nearest Class Center Accuracy: 0.8394

