Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_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: 0.0198909230530262
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: 0.01868194155395031
Inter Cos: 0.07130240648984909
Norm Quadratic Average: 37.418418884277344
Nearest Class Center Accuracy: 0.40438

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018535226583480835
Inter Cos: 0.05627928674221039
Norm Quadratic Average: 19.6088924407959
Nearest Class Center Accuracy: 0.52616

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.016189392656087875
Inter Cos: 0.040574174374341965
Norm Quadratic Average: 19.698579788208008
Nearest Class Center Accuracy: 0.61182

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02276771143078804
Inter Cos: 0.03556254133582115
Norm Quadratic Average: 12.956616401672363
Nearest Class Center Accuracy: 0.71928

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.036832332611083984
Inter Cos: 0.04518210515379906
Norm Quadratic Average: 16.042104721069336
Nearest Class Center Accuracy: 0.81824

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11979104578495026
Inter Cos: 0.09515447169542313
Norm Quadratic Average: 12.46876049041748
Nearest Class Center Accuracy: 0.94164

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48897573351860046
Inter Cos: 0.17510664463043213
Norm Quadratic Average: 10.043992042541504
Nearest Class Center Accuracy: 0.99438

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.61747741699219
Linear Weight Rank: 4031
Intra Cos: 0.776814341545105
Inter Cos: 0.23978844285011292
Norm Quadratic Average: 60.78752136230469
Nearest Class Center Accuracy: 0.98506

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.260942459106445
Linear Weight Rank: 3668
Intra Cos: 0.9519818425178528
Inter Cos: 0.004891457501798868
Norm Quadratic Average: 40.81928253173828
Nearest Class Center Accuracy: 0.99956

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.1035730838775635
Linear Weight Rank: 10
Intra Cos: 0.9395802021026611
Inter Cos: 0.019668500870466232
Norm Quadratic Average: 23.356096267700195
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9889006614685059
Inter Cos: 0.21071292459964752
Norm Quadratic Average: 19.08932876586914
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.9755885608673096
Accuracy: 0.8414
NC1 Within Class Collapse: 4.69526481628418
NC2 Equinorm: Features: 0.23623937368392944, Weights: 0.02088773250579834
NC2 Equiangle: Features: 0.10617825190226236, Weights: 0.08189387851291233
NC3 Self-Duality: 0.45817089080810547
NC4 NCC Mismatch: 0.06569999999999998

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: 0.017696330323815346
Inter Cos: 0.07284247130155563
Norm Quadratic Average: 37.38896179199219
Nearest Class Center Accuracy: 0.4214

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0170444268733263
Inter Cos: 0.057639069855213165
Norm Quadratic Average: 19.616466522216797
Nearest Class Center Accuracy: 0.5372

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01459452509880066
Inter Cos: 0.041531119495630264
Norm Quadratic Average: 19.723392486572266
Nearest Class Center Accuracy: 0.6149

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019479496404528618
Inter Cos: 0.03678809851408005
Norm Quadratic Average: 12.970295906066895
Nearest Class Center Accuracy: 0.6903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0291789211332798
Inter Cos: 0.0474030077457428
Norm Quadratic Average: 16.0228214263916
Nearest Class Center Accuracy: 0.7409

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08587199449539185
Inter Cos: 0.10384954512119293
Norm Quadratic Average: 12.382336616516113
Nearest Class Center Accuracy: 0.7827

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29935750365257263
Inter Cos: 0.21788129210472107
Norm Quadratic Average: 9.69318962097168
Nearest Class Center Accuracy: 0.8169

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.61747741699219
Linear Weight Rank: 4031
Intra Cos: 0.5634689331054688
Inter Cos: 0.42251598834991455
Norm Quadratic Average: 57.45288848876953
Nearest Class Center Accuracy: 0.7914

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.260942459106445
Linear Weight Rank: 3668
Intra Cos: 0.5614444017410278
Inter Cos: 0.2706812024116516
Norm Quadratic Average: 36.83476638793945
Nearest Class Center Accuracy: 0.8078

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.1035730838775635
Linear Weight Rank: 10
Intra Cos: 0.5493305921554565
Inter Cos: 0.251761794090271
Norm Quadratic Average: 21.36778450012207
Nearest Class Center Accuracy: 0.8198

Output Layer:
Intra Cos: 0.5933254361152649
Inter Cos: 0.3362593650817871
Norm Quadratic Average: 17.13418197631836
Nearest Class Center Accuracy: 0.834

