Model save path: ./New_Models/bn_True_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_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: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326322555541992
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02642892487347126
Inter Cos: 0.026743123307824135
Norm Quadratic Average: 41.07247543334961
Nearest Class Center Accuracy: 0.04876

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022287419065833092
Inter Cos: 0.022247683256864548
Norm Quadratic Average: 21.229814529418945
Nearest Class Center Accuracy: 0.06

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01834314875304699
Inter Cos: 0.019281331449747086
Norm Quadratic Average: 19.05817413330078
Nearest Class Center Accuracy: 0.069

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02302047424018383
Inter Cos: 0.02305659092962742
Norm Quadratic Average: 11.624434471130371
Nearest Class Center Accuracy: 0.07826

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029376309365034103
Inter Cos: 0.03038233518600464
Norm Quadratic Average: 11.871203422546387
Nearest Class Center Accuracy: 0.08392

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06741379201412201
Inter Cos: 0.058273863047361374
Norm Quadratic Average: 8.904962539672852
Nearest Class Center Accuracy: 0.09528

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2528171241283417
Inter Cos: 0.15383101999759674
Norm Quadratic Average: 8.196377754211426
Nearest Class Center Accuracy: 0.09976

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.676395416259766
Linear Weight Rank: 4030
Intra Cos: 0.6077755689620972
Inter Cos: 0.24318775534629822
Norm Quadratic Average: 40.63559341430664
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.34473419189453
Linear Weight Rank: 3655
Intra Cos: 0.7920522093772888
Inter Cos: 0.24178358912467957
Norm Quadratic Average: 32.95795440673828
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.105908393859863
Linear Weight Rank: 98
Intra Cos: 0.8508713841438293
Inter Cos: 0.2806888818740845
Norm Quadratic Average: 33.136810302734375
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9103992581367493
Inter Cos: 0.42312273383140564
Norm Quadratic Average: 52.22184371948242
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 2.9217936599731447
Accuracy: 0.5405
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2772625684738159, Weights: 0.0330968052148819
NC2 Equiangle: Features: 0.17129155322758838, Weights: 0.09742966777146464
NC3 Self-Duality: 0.4737739861011505
NC4 NCC Mismatch: 0.16369999999999996

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218780517578
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013107809238135815
Inter Cos: 0.26001474261283875
Norm Quadratic Average: 41.36945343017578
Nearest Class Center Accuracy: 0.2666

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015227613039314747
Inter Cos: 0.19789215922355652
Norm Quadratic Average: 21.389266967773438
Nearest Class Center Accuracy: 0.3906

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013101817108690739
Inter Cos: 0.1388663351535797
Norm Quadratic Average: 19.14338493347168
Nearest Class Center Accuracy: 0.505

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013057065196335316
Inter Cos: 0.13790100812911987
Norm Quadratic Average: 11.655599594116211
Nearest Class Center Accuracy: 0.5886

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013192676939070225
Inter Cos: 0.12468383461236954
Norm Quadratic Average: 11.851542472839355
Nearest Class Center Accuracy: 0.623

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022740308195352554
Inter Cos: 0.1916431337594986
Norm Quadratic Average: 8.801922798156738
Nearest Class Center Accuracy: 0.6099

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06424643099308014
Inter Cos: 0.366122841835022
Norm Quadratic Average: 7.7473626136779785
Nearest Class Center Accuracy: 0.5799

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.676395416259766
Linear Weight Rank: 4030
Intra Cos: 0.15961848199367523
Inter Cos: 0.462511271238327
Norm Quadratic Average: 34.995452880859375
Nearest Class Center Accuracy: 0.538

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.34473419189453
Linear Weight Rank: 3655
Intra Cos: 0.18456003069877625
Inter Cos: 0.461790531873703
Norm Quadratic Average: 26.7071533203125
Nearest Class Center Accuracy: 0.5375

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.105908393859863
Linear Weight Rank: 98
Intra Cos: 0.1853412687778473
Inter Cos: 0.5307992100715637
Norm Quadratic Average: 26.633852005004883
Nearest Class Center Accuracy: 0.5367

Output Layer:
Intra Cos: 0.20464172959327698
Inter Cos: 0.6654481291770935
Norm Quadratic Average: 42.17321014404297
Nearest Class Center Accuracy: 0.5308

