Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0005.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: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11681591719388962
Inter Cos: 0.1380065232515335
Norm Quadratic Average: 39.93241882324219
Nearest Class Center Accuracy: 0.81985

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19120065867900848
Inter Cos: 0.17042793333530426
Norm Quadratic Average: 39.99643325805664
Nearest Class Center Accuracy: 0.8624833333333334

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22282563149929047
Inter Cos: 0.18428149819374084
Norm Quadratic Average: 39.289100646972656
Nearest Class Center Accuracy: 0.8998333333333334

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2501467764377594
Inter Cos: 0.16833730041980743
Norm Quadratic Average: 18.178762435913086
Nearest Class Center Accuracy: 0.94905

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38662245869636536
Inter Cos: 0.22939801216125488
Norm Quadratic Average: 11.069014549255371
Nearest Class Center Accuracy: 0.97435

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5378594398498535
Inter Cos: 0.2927653193473816
Norm Quadratic Average: 5.77083158493042
Nearest Class Center Accuracy: 0.9911666666666666

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8022007942199707
Inter Cos: 0.33395588397979736
Norm Quadratic Average: 4.835049152374268
Nearest Class Center Accuracy: 0.9974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.765800476074219
Linear Weight Rank: 4031
Intra Cos: 0.8788534998893738
Inter Cos: 0.24563537538051605
Norm Quadratic Average: 26.4280948638916
Nearest Class Center Accuracy: 0.9984833333333333

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.451338768005371
Linear Weight Rank: 3666
Intra Cos: 0.9142450094223022
Inter Cos: 0.21921135485172272
Norm Quadratic Average: 23.515865325927734
Nearest Class Center Accuracy: 0.9993333333333333

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.6228139400482178
Linear Weight Rank: 10
Intra Cos: 0.9210533499717712
Inter Cos: 0.21137534081935883
Norm Quadratic Average: 20.83791732788086
Nearest Class Center Accuracy: 0.9996

Output Layer:
Intra Cos: 0.9407633543014526
Inter Cos: 0.3142526149749756
Norm Quadratic Average: 20.676069259643555
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.02059005724832532
Accuracy: 0.9936
NC1 Within Class Collapse: 0.7739547491073608
NC2 Equinorm: Features: 0.11261332780122757, Weights: 0.04122352600097656
NC2 Equiangle: Features: 0.20658851199679903, Weights: 0.12704958385891385
NC3 Self-Duality: 0.10842297226190567
NC4 NCC Mismatch: 0.0031999999999999806

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
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: 0.13008669018745422
Inter Cos: 0.150660440325737
Norm Quadratic Average: 39.89262390136719
Nearest Class Center Accuracy: 0.8336

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2057318240404129
Inter Cos: 0.17958901822566986
Norm Quadratic Average: 39.85654830932617
Nearest Class Center Accuracy: 0.8778

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23689429461956024
Inter Cos: 0.19639837741851807
Norm Quadratic Average: 39.18207931518555
Nearest Class Center Accuracy: 0.9105

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2621520161628723
Inter Cos: 0.18171867728233337
Norm Quadratic Average: 18.14592742919922
Nearest Class Center Accuracy: 0.956

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4006851315498352
Inter Cos: 0.2454703152179718
Norm Quadratic Average: 11.074945449829102
Nearest Class Center Accuracy: 0.9758

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5490790605545044
Inter Cos: 0.30912432074546814
Norm Quadratic Average: 5.797679901123047
Nearest Class Center Accuracy: 0.9865

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8111332654953003
Inter Cos: 0.3459585905075073
Norm Quadratic Average: 4.874844551086426
Nearest Class Center Accuracy: 0.9898

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.765800476074219
Linear Weight Rank: 4031
Intra Cos: 0.8817117810249329
Inter Cos: 0.2614571154117584
Norm Quadratic Average: 26.64513397216797
Nearest Class Center Accuracy: 0.9911

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.451338768005371
Linear Weight Rank: 3666
Intra Cos: 0.9153237342834473
Inter Cos: 0.23462709784507751
Norm Quadratic Average: 23.70313835144043
Nearest Class Center Accuracy: 0.992

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.6228139400482178
Linear Weight Rank: 10
Intra Cos: 0.9213971495628357
Inter Cos: 0.20131437480449677
Norm Quadratic Average: 21.000972747802734
Nearest Class Center Accuracy: 0.9922

Output Layer:
Intra Cos: 0.9363929629325867
Inter Cos: 0.29018038511276245
Norm Quadratic Average: 20.83417320251465
Nearest Class Center Accuracy: 0.9932

