Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_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: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02334532141685486
Inter Cos: 0.08919479697942734
Norm Quadratic Average: 26.8959903717041
Nearest Class Center Accuracy: 0.39356

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025965649634599686
Inter Cos: 0.07867737114429474
Norm Quadratic Average: 24.048002243041992
Nearest Class Center Accuracy: 0.4929

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024962330237030983
Inter Cos: 0.0630221962928772
Norm Quadratic Average: 25.321168899536133
Nearest Class Center Accuracy: 0.5803

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029636090621352196
Inter Cos: 0.05205323547124863
Norm Quadratic Average: 11.583538055419922
Nearest Class Center Accuracy: 0.6839

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.048698414117097855
Inter Cos: 0.05844828486442566
Norm Quadratic Average: 6.772397041320801
Nearest Class Center Accuracy: 0.76186

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14738482236862183
Inter Cos: 0.1391608864068985
Norm Quadratic Average: 2.648878812789917
Nearest Class Center Accuracy: 0.89614

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5705209970474243
Inter Cos: 0.22914627194404602
Norm Quadratic Average: 1.6197000741958618
Nearest Class Center Accuracy: 0.9974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.43987464904785
Linear Weight Rank: 4031
Intra Cos: 0.8275540471076965
Inter Cos: 0.20234355330467224
Norm Quadratic Average: 11.300620079040527
Nearest Class Center Accuracy: 0.9994

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.019856452941895
Linear Weight Rank: 3665
Intra Cos: 0.8915796279907227
Inter Cos: 0.1378839761018753
Norm Quadratic Average: 12.086108207702637
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.723639965057373
Linear Weight Rank: 10
Intra Cos: 0.9044004082679749
Inter Cos: 0.17830194532871246
Norm Quadratic Average: 13.542243003845215
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9306756854057312
Inter Cos: 0.3555464744567871
Norm Quadratic Average: 16.741113662719727
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.8897591136932373
Accuracy: 0.8177
NC1 Within Class Collapse: 5.468498229980469
NC2 Equinorm: Features: 0.20501820743083954, Weights: 0.028562255203723907
NC2 Equiangle: Features: 0.19778760274251303, Weights: 0.056589264339870875
NC3 Self-Duality: 0.15269817411899567
NC4 NCC Mismatch: 0.0484

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021637186408042908
Inter Cos: 0.0900031328201294
Norm Quadratic Average: 26.879940032958984
Nearest Class Center Accuracy: 0.4084

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02458019182085991
Inter Cos: 0.07989096641540527
Norm Quadratic Average: 24.056785583496094
Nearest Class Center Accuracy: 0.4978

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023110128939151764
Inter Cos: 0.0636930912733078
Norm Quadratic Average: 25.346906661987305
Nearest Class Center Accuracy: 0.583

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02610408328473568
Inter Cos: 0.05328899249434471
Norm Quadratic Average: 11.590576171875
Nearest Class Center Accuracy: 0.6644

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04164726287126541
Inter Cos: 0.0607331320643425
Norm Quadratic Average: 6.762515544891357
Nearest Class Center Accuracy: 0.7097

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11479970067739487
Inter Cos: 0.1445387899875641
Norm Quadratic Average: 2.6310672760009766
Nearest Class Center Accuracy: 0.7593

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34237849712371826
Inter Cos: 0.2697996497154236
Norm Quadratic Average: 1.5711301565170288
Nearest Class Center Accuracy: 0.8107

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.43987464904785
Linear Weight Rank: 4031
Intra Cos: 0.48290449380874634
Inter Cos: 0.3228607475757599
Norm Quadratic Average: 10.749048233032227
Nearest Class Center Accuracy: 0.8097

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.019856452941895
Linear Weight Rank: 3665
Intra Cos: 0.5040517449378967
Inter Cos: 0.30495283007621765
Norm Quadratic Average: 11.402694702148438
Nearest Class Center Accuracy: 0.8115

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.723639965057373
Linear Weight Rank: 10
Intra Cos: 0.5015303492546082
Inter Cos: 0.30107545852661133
Norm Quadratic Average: 12.754384994506836
Nearest Class Center Accuracy: 0.8155

Output Layer:
Intra Cos: 0.524872362613678
Inter Cos: 0.3895101547241211
Norm Quadratic Average: 15.730101585388184
Nearest Class Center Accuracy: 0.8172

