Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311887949705124
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: 0.10100708901882172
Inter Cos: 0.1239997148513794
Norm Quadratic Average: 7.497424602508545
Nearest Class Center Accuracy: 0.832875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1546478122472763
Inter Cos: 0.1382085084915161
Norm Quadratic Average: 4.528892517089844
Nearest Class Center Accuracy: 0.86075

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17187996208667755
Inter Cos: 0.13609270751476288
Norm Quadratic Average: 4.606786251068115
Nearest Class Center Accuracy: 0.89475

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24557621777057648
Inter Cos: 0.13509994745254517
Norm Quadratic Average: 2.7380692958831787
Nearest Class Center Accuracy: 0.95925

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3253079056739807
Inter Cos: 0.15172375738620758
Norm Quadratic Average: 2.749535083770752
Nearest Class Center Accuracy: 0.99325

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5748432278633118
Inter Cos: 0.1658829152584076
Norm Quadratic Average: 2.0832645893096924
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9199929237365723
Inter Cos: 0.15120014548301697
Norm Quadratic Average: 2.2262349128723145
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 9.278681755065918
Linear Weight Rank: 4031
Intra Cos: 0.9953579902648926
Inter Cos: 0.1705913245677948
Norm Quadratic Average: 28.005956649780273
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.079195499420166
Linear Weight Rank: 3666
Intra Cos: 0.9986326098442078
Inter Cos: 0.18272548913955688
Norm Quadratic Average: 16.133190155029297
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7647955417633057
Linear Weight Rank: 10
Intra Cos: 0.9988006353378296
Inter Cos: 0.19804903864860535
Norm Quadratic Average: 10.481443405151367
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9991177320480347
Inter Cos: 0.325519323348999
Norm Quadratic Average: 7.605043888092041
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08542439317703247
Accuracy: 0.989
NC1 Within Class Collapse: 0.5777466297149658
NC2 Equinorm: Features: 0.06144765764474869, Weights: 0.024733033031225204
NC2 Equiangle: Features: 0.21643687354193794, Weights: 0.16952294243706598
NC3 Self-Duality: 0.05144116282463074
NC4 NCC Mismatch: 0.0020000000000000018

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.12287216633558273
Inter Cos: 0.12858864665031433
Norm Quadratic Average: 7.362464427947998
Nearest Class Center Accuracy: 0.826

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15833158791065216
Inter Cos: 0.16429689526557922
Norm Quadratic Average: 4.471546649932861
Nearest Class Center Accuracy: 0.857

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17631717026233673
Inter Cos: 0.16418802738189697
Norm Quadratic Average: 4.563275337219238
Nearest Class Center Accuracy: 0.8955

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23895153403282166
Inter Cos: 0.15793950855731964
Norm Quadratic Average: 2.7265079021453857
Nearest Class Center Accuracy: 0.9455

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3175203800201416
Inter Cos: 0.17142608761787415
Norm Quadratic Average: 2.7403135299682617
Nearest Class Center Accuracy: 0.973

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5190047025680542
Inter Cos: 0.16922976076602936
Norm Quadratic Average: 2.042844295501709
Nearest Class Center Accuracy: 0.9845

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8368606567382812
Inter Cos: 0.17140734195709229
Norm Quadratic Average: 2.1335630416870117
Nearest Class Center Accuracy: 0.9865

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 9.278681755065918
Linear Weight Rank: 4031
Intra Cos: 0.9315588474273682
Inter Cos: 0.1859591007232666
Norm Quadratic Average: 26.57746124267578
Nearest Class Center Accuracy: 0.9865

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.079195499420166
Linear Weight Rank: 3666
Intra Cos: 0.9364547729492188
Inter Cos: 0.1892923265695572
Norm Quadratic Average: 15.3280668258667
Nearest Class Center Accuracy: 0.989

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7647955417633057
Linear Weight Rank: 10
Intra Cos: 0.9349669218063354
Inter Cos: 0.19391781091690063
Norm Quadratic Average: 9.981532096862793
Nearest Class Center Accuracy: 0.989

Output Layer:
Intra Cos: 0.9426906108856201
Inter Cos: 0.3100670576095581
Norm Quadratic Average: 7.227959156036377
Nearest Class Center Accuracy: 0.989

