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_0.0005.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: 27.59717559814453
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018519015982747078
Inter Cos: 0.07189052551984787
Norm Quadratic Average: 23.401247024536133
Nearest Class Center Accuracy: 0.40304

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01971128024160862
Inter Cos: 0.05410829558968544
Norm Quadratic Average: 11.54662036895752
Nearest Class Center Accuracy: 0.53284

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01520542986690998
Inter Cos: 0.04044417664408684
Norm Quadratic Average: 10.258062362670898
Nearest Class Center Accuracy: 0.61488

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020760202780365944
Inter Cos: 0.033770449459552765
Norm Quadratic Average: 6.464597225189209
Nearest Class Center Accuracy: 0.73708

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.033597081899642944
Inter Cos: 0.03510434553027153
Norm Quadratic Average: 6.584167003631592
Nearest Class Center Accuracy: 0.83928

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12672379612922668
Inter Cos: 0.07767821848392487
Norm Quadratic Average: 6.113351345062256
Nearest Class Center Accuracy: 0.95122

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5387276411056519
Inter Cos: 0.15355989336967468
Norm Quadratic Average: 5.278946876525879
Nearest Class Center Accuracy: 0.99838

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.374433517456055
Linear Weight Rank: 4031
Intra Cos: 0.8326107859611511
Inter Cos: 0.11255817860364914
Norm Quadratic Average: 38.723270416259766
Nearest Class Center Accuracy: 0.99848

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.92935848236084
Linear Weight Rank: 3665
Intra Cos: 0.9550065994262695
Inter Cos: -0.02722829207777977
Norm Quadratic Average: 27.16564178466797
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.8100907802581787
Linear Weight Rank: 10
Intra Cos: 0.9442014694213867
Inter Cos: 0.018619995564222336
Norm Quadratic Average: 18.501998901367188
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.990101158618927
Inter Cos: 0.22900637984275818
Norm Quadratic Average: 15.749216079711914
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.8370089232683182
Accuracy: 0.8438
NC1 Within Class Collapse: 4.311153411865234
NC2 Equinorm: Features: 0.19290317595005035, Weights: 0.028499936684966087
NC2 Equiangle: Features: 0.11610471937391494, Weights: 0.060004933675130205
NC3 Self-Duality: 0.2234407216310501
NC4 NCC Mismatch: 0.04520000000000002

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: 0.01748698204755783
Inter Cos: 0.0734751746058464
Norm Quadratic Average: 23.38605499267578
Nearest Class Center Accuracy: 0.4189

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018571902066469193
Inter Cos: 0.05567381903529167
Norm Quadratic Average: 11.550217628479004
Nearest Class Center Accuracy: 0.5408

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014058435335755348
Inter Cos: 0.04136905074119568
Norm Quadratic Average: 10.26655387878418
Nearest Class Center Accuracy: 0.6216

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017755765467882156
Inter Cos: 0.034680966287851334
Norm Quadratic Average: 6.465285301208496
Nearest Class Center Accuracy: 0.7017

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025733070448040962
Inter Cos: 0.03737661987543106
Norm Quadratic Average: 6.5574235916137695
Nearest Class Center Accuracy: 0.7498

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08960075676441193
Inter Cos: 0.08570300787687302
Norm Quadratic Average: 6.035837173461914
Nearest Class Center Accuracy: 0.7906

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30200380086898804
Inter Cos: 0.21596993505954742
Norm Quadratic Average: 5.023111343383789
Nearest Class Center Accuracy: 0.8244

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.374433517456055
Linear Weight Rank: 4031
Intra Cos: 0.5563821792602539
Inter Cos: 0.3282793164253235
Norm Quadratic Average: 35.83538818359375
Nearest Class Center Accuracy: 0.8106

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.92935848236084
Linear Weight Rank: 3665
Intra Cos: 0.5345285534858704
Inter Cos: 0.2507795989513397
Norm Quadratic Average: 24.371061325073242
Nearest Class Center Accuracy: 0.8257

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.8100907802581787
Linear Weight Rank: 10
Intra Cos: 0.5273273587226868
Inter Cos: 0.25436627864837646
Norm Quadratic Average: 16.86168098449707
Nearest Class Center Accuracy: 0.8355

Output Layer:
Intra Cos: 0.5686571002006531
Inter Cos: 0.3208317756652832
Norm Quadratic Average: 14.145697593688965
Nearest Class Center Accuracy: 0.8413

