Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10128834843635559
Inter Cos: 0.11971233040094376
Norm Quadratic Average: 70.3713150024414
Nearest Class Center Accuracy: 0.831

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14641448855400085
Inter Cos: 0.1358887106180191
Norm Quadratic Average: 44.24550247192383
Nearest Class Center Accuracy: 0.85925

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14883843064308167
Inter Cos: 0.12208963185548782
Norm Quadratic Average: 45.52757263183594
Nearest Class Center Accuracy: 0.88075

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17554393410682678
Inter Cos: 0.10365483164787292
Norm Quadratic Average: 28.05431365966797
Nearest Class Center Accuracy: 0.915125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18758836388587952
Inter Cos: 0.09178046882152557
Norm Quadratic Average: 28.925989151000977
Nearest Class Center Accuracy: 0.940125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.205733984708786
Inter Cos: 0.1235150396823883
Norm Quadratic Average: 20.005352020263672
Nearest Class Center Accuracy: 0.97875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3202185332775116
Inter Cos: 0.10670961439609528
Norm Quadratic Average: 15.03380298614502
Nearest Class Center Accuracy: 0.998125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75471496582031
Linear Weight Rank: 4031
Intra Cos: 0.5677056908607483
Inter Cos: 0.12642179429531097
Norm Quadratic Average: 101.19251251220703
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.23847198486328
Linear Weight Rank: 3671
Intra Cos: 0.7225577235221863
Inter Cos: 0.14300595223903656
Norm Quadratic Average: 50.011497497558594
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9309618473052979
Linear Weight Rank: 10
Intra Cos: 0.8296347856521606
Inter Cos: 0.15638594329357147
Norm Quadratic Average: 29.672361373901367
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9270431995391846
Inter Cos: 0.2524205446243286
Norm Quadratic Average: 15.434815406799316
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08339813077449798
Accuracy: 0.973
NC1 Within Class Collapse: 1.574797511100769
NC2 Equinorm: Features: 0.05491214990615845, Weights: 0.015393348410725594
NC2 Equiangle: Features: 0.2046510696411133, Weights: 0.08647201326158312
NC3 Self-Duality: 0.5199874639511108
NC4 NCC Mismatch: 0.0040000000000000036

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957791447639465
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12397290021181107
Inter Cos: 0.12825772166252136
Norm Quadratic Average: 69.446044921875
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15633262693881989
Inter Cos: 0.1525764912366867
Norm Quadratic Average: 43.81912612915039
Nearest Class Center Accuracy: 0.85

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15220174193382263
Inter Cos: 0.1362900584936142
Norm Quadratic Average: 45.17588806152344
Nearest Class Center Accuracy: 0.875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1669466495513916
Inter Cos: 0.12513944506645203
Norm Quadratic Average: 28.012531280517578
Nearest Class Center Accuracy: 0.9095

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18084277212619781
Inter Cos: 0.11422652751207352
Norm Quadratic Average: 28.912734985351562
Nearest Class Center Accuracy: 0.925

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20755517482757568
Inter Cos: 0.13754235208034515
Norm Quadratic Average: 19.991085052490234
Nearest Class Center Accuracy: 0.9485

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28448960185050964
Inter Cos: 0.10083857923746109
Norm Quadratic Average: 14.902382850646973
Nearest Class Center Accuracy: 0.9695

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75471496582031
Linear Weight Rank: 4031
Intra Cos: 0.4679943919181824
Inter Cos: 0.12010680139064789
Norm Quadratic Average: 98.90607452392578
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.23847198486328
Linear Weight Rank: 3671
Intra Cos: 0.6079389452934265
Inter Cos: 0.13827811181545258
Norm Quadratic Average: 48.562767028808594
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9309618473052979
Linear Weight Rank: 10
Intra Cos: 0.7123154401779175
Inter Cos: 0.14810487627983093
Norm Quadratic Average: 28.727521896362305
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.8197901844978333
Inter Cos: 0.23422349989414215
Norm Quadratic Average: 14.886868476867676
Nearest Class Center Accuracy: 0.972

