Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 0.11371058225631714
Norm Quadratic Average: 27.691619873046875
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023858683183789253
Inter Cos: 0.09996725618839264
Norm Quadratic Average: 74.82618713378906
Nearest Class Center Accuracy: 0.335

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026257451623678207
Inter Cos: 0.0889628678560257
Norm Quadratic Average: 56.386573791503906
Nearest Class Center Accuracy: 0.3735

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022677237167954445
Inter Cos: 0.06927663832902908
Norm Quadratic Average: 59.97816467285156
Nearest Class Center Accuracy: 0.40625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031871095299720764
Inter Cos: 0.07702592015266418
Norm Quadratic Average: 38.403499603271484
Nearest Class Center Accuracy: 0.421125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031094681471586227
Inter Cos: 0.06697655469179153
Norm Quadratic Average: 39.13172149658203
Nearest Class Center Accuracy: 0.463375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.041753221303224564
Inter Cos: 0.07497948408126831
Norm Quadratic Average: 25.05790901184082
Nearest Class Center Accuracy: 0.565625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06703191250562668
Inter Cos: 0.0762922540307045
Norm Quadratic Average: 17.73835563659668
Nearest Class Center Accuracy: 0.864875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79784393310547
Linear Weight Rank: 4031
Intra Cos: 0.20972856879234314
Inter Cos: 0.11150903254747391
Norm Quadratic Average: 95.78160858154297
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.48842239379883
Linear Weight Rank: 3670
Intra Cos: 0.4805988669395447
Inter Cos: 0.20399783551692963
Norm Quadratic Average: 47.630882263183594
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2736597061157227
Linear Weight Rank: 10
Intra Cos: 0.7091370224952698
Inter Cos: 0.3068557679653168
Norm Quadratic Average: 32.14458084106445
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8883598446846008
Inter Cos: 0.47893059253692627
Norm Quadratic Average: 21.282529830932617
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 2.159903343200684
Accuracy: 0.576
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.21161291003227234, Weights: 0.013961195945739746
NC2 Equiangle: Features: 0.43457268608940974, Weights: 0.09251310560438368
NC3 Self-Duality: 0.6114365458488464
NC4 NCC Mismatch: 0.15300000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480459228157997
Inter Cos: 0.09352367371320724
Norm Quadratic Average: 27.53066635131836
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02310146391391754
Inter Cos: 0.08625195175409317
Norm Quadratic Average: 74.39909362792969
Nearest Class Center Accuracy: 0.352

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026386713609099388
Inter Cos: 0.07726815342903137
Norm Quadratic Average: 56.09783172607422
Nearest Class Center Accuracy: 0.403

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02294372394680977
Inter Cos: 0.06030111387372017
Norm Quadratic Average: 59.76616668701172
Nearest Class Center Accuracy: 0.444

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029552454128861427
Inter Cos: 0.06997913867235184
Norm Quadratic Average: 38.26953125
Nearest Class Center Accuracy: 0.4495

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027945173904299736
Inter Cos: 0.06002961844205856
Norm Quadratic Average: 39.038570404052734
Nearest Class Center Accuracy: 0.4815

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031347550451755524
Inter Cos: 0.07262058556079865
Norm Quadratic Average: 24.965740203857422
Nearest Class Center Accuracy: 0.5065

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034469421952962875
Inter Cos: 0.06592626124620438
Norm Quadratic Average: 17.5859317779541
Nearest Class Center Accuracy: 0.5685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79784393310547
Linear Weight Rank: 4031
Intra Cos: 0.06049201264977455
Inter Cos: 0.11114407330751419
Norm Quadratic Average: 92.04997253417969
Nearest Class Center Accuracy: 0.602

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.48842239379883
Linear Weight Rank: 3670
Intra Cos: 0.12602096796035767
Inter Cos: 0.213320791721344
Norm Quadratic Average: 43.53245162963867
Nearest Class Center Accuracy: 0.5755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2736597061157227
Linear Weight Rank: 10
Intra Cos: 0.19298622012138367
Inter Cos: 0.3299565017223358
Norm Quadratic Average: 28.292573928833008
Nearest Class Center Accuracy: 0.569

Output Layer:
Intra Cos: 0.2656579315662384
Inter Cos: 0.47994083166122437
Norm Quadratic Average: 18.218900680541992
Nearest Class Center Accuracy: 0.5585

