Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.0003.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: 27.59717559814453
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018727988004684448
Inter Cos: 0.0736493319272995
Norm Quadratic Average: 37.46958541870117
Nearest Class Center Accuracy: 0.40422

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01876448653638363
Inter Cos: 0.05583925172686577
Norm Quadratic Average: 19.6306095123291
Nearest Class Center Accuracy: 0.53188

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014933601953089237
Inter Cos: 0.04019784927368164
Norm Quadratic Average: 19.721830368041992
Nearest Class Center Accuracy: 0.60886

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02117178402841091
Inter Cos: 0.03520333394408226
Norm Quadratic Average: 13.025390625
Nearest Class Center Accuracy: 0.71848

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03702929615974426
Inter Cos: 0.03988049179315567
Norm Quadratic Average: 15.986858367919922
Nearest Class Center Accuracy: 0.81606

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11632011085748672
Inter Cos: 0.09747310727834702
Norm Quadratic Average: 12.508995056152344
Nearest Class Center Accuracy: 0.9436

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4690409302711487
Inter Cos: 0.16221337020397186
Norm Quadratic Average: 9.988029479980469
Nearest Class Center Accuracy: 0.99546

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.618961334228516
Linear Weight Rank: 4031
Intra Cos: 0.7835465669631958
Inter Cos: 0.223690465092659
Norm Quadratic Average: 59.77838134765625
Nearest Class Center Accuracy: 0.98622

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.269807815551758
Linear Weight Rank: 3668
Intra Cos: 0.9478911757469177
Inter Cos: 0.01756438985466957
Norm Quadratic Average: 40.4566535949707
Nearest Class Center Accuracy: 0.99938

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.0917956829071045
Linear Weight Rank: 10
Intra Cos: 0.9363553524017334
Inter Cos: 0.0505668967962265
Norm Quadratic Average: 23.25665855407715
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9882771372795105
Inter Cos: 0.3563308119773865
Norm Quadratic Average: 19.18307113647461
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.9805112553596497
Accuracy: 0.8391
NC1 Within Class Collapse: 4.668972969055176
NC2 Equinorm: Features: 0.2394513040781021, Weights: 0.021263808012008667
NC2 Equiangle: Features: 0.12132977379692925, Weights: 0.08232723871866862
NC3 Self-Duality: 0.4516509473323822
NC4 NCC Mismatch: 0.0625

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: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017503557726740837
Inter Cos: 0.07548116147518158
Norm Quadratic Average: 37.43932342529297
Nearest Class Center Accuracy: 0.4224

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017547516152262688
Inter Cos: 0.057272978127002716
Norm Quadratic Average: 19.637468338012695
Nearest Class Center Accuracy: 0.5425

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01365977805107832
Inter Cos: 0.04098883271217346
Norm Quadratic Average: 19.741910934448242
Nearest Class Center Accuracy: 0.6107

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017727289348840714
Inter Cos: 0.03658223897218704
Norm Quadratic Average: 13.034141540527344
Nearest Class Center Accuracy: 0.6896

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.028614653274416924
Inter Cos: 0.04189130663871765
Norm Quadratic Average: 15.949834823608398
Nearest Class Center Accuracy: 0.7384

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08041784912347794
Inter Cos: 0.10295508801937103
Norm Quadratic Average: 12.412623405456543
Nearest Class Center Accuracy: 0.7866

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2867457866668701
Inter Cos: 0.20565922558307648
Norm Quadratic Average: 9.645389556884766
Nearest Class Center Accuracy: 0.8182

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.618961334228516
Linear Weight Rank: 4031
Intra Cos: 0.5731111764907837
Inter Cos: 0.3986568748950958
Norm Quadratic Average: 56.70222091674805
Nearest Class Center Accuracy: 0.7942

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.269807815551758
Linear Weight Rank: 3668
Intra Cos: 0.5681155920028687
Inter Cos: 0.275829017162323
Norm Quadratic Average: 36.67140197753906
Nearest Class Center Accuracy: 0.8064

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.0917956829071045
Linear Weight Rank: 10
Intra Cos: 0.5499403476715088
Inter Cos: 0.2594858705997467
Norm Quadratic Average: 21.34761619567871
Nearest Class Center Accuracy: 0.8208

Output Layer:
Intra Cos: 0.5778476595878601
Inter Cos: 0.36107638478279114
Norm Quadratic Average: 17.295167922973633
Nearest Class Center Accuracy: 0.835

