Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450400352478027
Inter Cos: 0.11371058970689774
Norm Quadratic Average: 27.691621780395508
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026594657450914383
Inter Cos: 0.1016131043434143
Norm Quadratic Average: 75.63138580322266
Nearest Class Center Accuracy: 0.34075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031130004674196243
Inter Cos: 0.09013676643371582
Norm Quadratic Average: 55.006378173828125
Nearest Class Center Accuracy: 0.379

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027653776109218597
Inter Cos: 0.07259538769721985
Norm Quadratic Average: 59.9699821472168
Nearest Class Center Accuracy: 0.407125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.035515155643224716
Inter Cos: 0.07999677211046219
Norm Quadratic Average: 38.11638259887695
Nearest Class Center Accuracy: 0.431375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03380368649959564
Inter Cos: 0.06868026405572891
Norm Quadratic Average: 39.06954574584961
Nearest Class Center Accuracy: 0.47025

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.046978529542684555
Inter Cos: 0.08022793382406235
Norm Quadratic Average: 25.17810821533203
Nearest Class Center Accuracy: 0.56825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06694076210260391
Inter Cos: 0.07879509031772614
Norm Quadratic Average: 17.705533981323242
Nearest Class Center Accuracy: 0.8725

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80126953125
Linear Weight Rank: 4031
Intra Cos: 0.20437918603420258
Inter Cos: 0.10855501890182495
Norm Quadratic Average: 95.89969635009766
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50164794921875
Linear Weight Rank: 3671
Intra Cos: 0.4745122492313385
Inter Cos: 0.20458216965198517
Norm Quadratic Average: 48.141639709472656
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.285670757293701
Linear Weight Rank: 10
Intra Cos: 0.7128790616989136
Inter Cos: 0.2939249277114868
Norm Quadratic Average: 32.340415954589844
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8948740363121033
Inter Cos: 0.5029059052467346
Norm Quadratic Average: 21.606216430664062
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 2.1083154830932616
Accuracy: 0.5915
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.19943958520889282, Weights: 0.020629217848181725
NC2 Equiangle: Features: 0.44222225613064237, Weights: 0.0905181884765625
NC3 Self-Duality: 0.601111650466919
NC4 NCC Mismatch: 0.15200000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480459228157997
Inter Cos: 0.09352368116378784
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024444829672574997
Inter Cos: 0.08928923308849335
Norm Quadratic Average: 75.6002197265625
Nearest Class Center Accuracy: 0.354

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02981513924896717
Inter Cos: 0.08529794216156006
Norm Quadratic Average: 54.99673843383789
Nearest Class Center Accuracy: 0.396

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027321798726916313
Inter Cos: 0.06697838753461838
Norm Quadratic Average: 60.02500915527344
Nearest Class Center Accuracy: 0.4285

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03374326974153519
Inter Cos: 0.08165036141872406
Norm Quadratic Average: 38.10817337036133
Nearest Class Center Accuracy: 0.45

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03086788021028042
Inter Cos: 0.06858478486537933
Norm Quadratic Average: 39.03916931152344
Nearest Class Center Accuracy: 0.473

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03574258089065552
Inter Cos: 0.0804852694272995
Norm Quadratic Average: 25.087278366088867
Nearest Class Center Accuracy: 0.4865

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0369742251932621
Inter Cos: 0.07245595753192902
Norm Quadratic Average: 17.534515380859375
Nearest Class Center Accuracy: 0.5715

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80126953125
Linear Weight Rank: 4031
Intra Cos: 0.0677514374256134
Inter Cos: 0.11119269579648972
Norm Quadratic Average: 91.92424011230469
Nearest Class Center Accuracy: 0.625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50164794921875
Linear Weight Rank: 3671
Intra Cos: 0.141355499625206
Inter Cos: 0.20640788972377777
Norm Quadratic Average: 43.85224151611328
Nearest Class Center Accuracy: 0.6005

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.285670757293701
Linear Weight Rank: 10
Intra Cos: 0.21379214525222778
Inter Cos: 0.314212441444397
Norm Quadratic Average: 28.32876205444336
Nearest Class Center Accuracy: 0.585

Output Layer:
Intra Cos: 0.2946920096874237
Inter Cos: 0.45916616916656494
Norm Quadratic Average: 18.42579460144043
Nearest Class Center Accuracy: 0.564

