Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946064859628677
Inter Cos: 0.11311884224414825
Norm Quadratic Average: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10114361345767975
Inter Cos: 0.11754652112722397
Norm Quadratic Average: 56.321044921875
Nearest Class Center Accuracy: 0.8365

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15405608713626862
Inter Cos: 0.14106205105781555
Norm Quadratic Average: 34.37986373901367
Nearest Class Center Accuracy: 0.861

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15639324486255646
Inter Cos: 0.13111913204193115
Norm Quadratic Average: 35.69954299926758
Nearest Class Center Accuracy: 0.882125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17967191338539124
Inter Cos: 0.11241323500871658
Norm Quadratic Average: 21.91346549987793
Nearest Class Center Accuracy: 0.9205

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18935133516788483
Inter Cos: 0.10021486133337021
Norm Quadratic Average: 22.526470184326172
Nearest Class Center Accuracy: 0.95025

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22804051637649536
Inter Cos: 0.08174115419387817
Norm Quadratic Average: 15.550477027893066
Nearest Class Center Accuracy: 0.988625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3702751100063324
Inter Cos: 0.07922717183828354
Norm Quadratic Average: 11.893576622009277
Nearest Class Center Accuracy: 0.999375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.73046875
Linear Weight Rank: 4031
Intra Cos: 0.6600327491760254
Inter Cos: 0.07896362245082855
Norm Quadratic Average: 87.69808197021484
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.372312545776367
Linear Weight Rank: 3670
Intra Cos: 0.8174134492874146
Inter Cos: 0.09031327813863754
Norm Quadratic Average: 40.67820358276367
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.718390703201294
Linear Weight Rank: 10
Intra Cos: 0.8907982110977173
Inter Cos: 0.13520225882530212
Norm Quadratic Average: 23.22062110900879
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9327499866485596
Inter Cos: 0.22331444919109344
Norm Quadratic Average: 11.677191734313965
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06758320474624634
Accuracy: 0.979
NC1 Within Class Collapse: 1.3526883125305176
NC2 Equinorm: Features: 0.05245897173881531, Weights: 0.012523730285465717
NC2 Equiangle: Features: 0.16595772637261286, Weights: 0.07375988960266114
NC3 Self-Duality: 0.3647400736808777
NC4 NCC Mismatch: 0.0034999999999999476

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133810341358185
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: 0.12328227609395981
Inter Cos: 0.1275327503681183
Norm Quadratic Average: 55.71430587768555
Nearest Class Center Accuracy: 0.833

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15581341087818146
Inter Cos: 0.16016583144664764
Norm Quadratic Average: 34.226688385009766
Nearest Class Center Accuracy: 0.857

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15195369720458984
Inter Cos: 0.14482450485229492
Norm Quadratic Average: 35.579315185546875
Nearest Class Center Accuracy: 0.873

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16943159699440002
Inter Cos: 0.11872629076242447
Norm Quadratic Average: 21.926828384399414
Nearest Class Center Accuracy: 0.913

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17589691281318665
Inter Cos: 0.11277209967374802
Norm Quadratic Average: 22.558351516723633
Nearest Class Center Accuracy: 0.9385

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22146539390087128
Inter Cos: 0.08248088508844376
Norm Quadratic Average: 15.55315113067627
Nearest Class Center Accuracy: 0.967

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3306233286857605
Inter Cos: 0.09516915678977966
Norm Quadratic Average: 11.826674461364746
Nearest Class Center Accuracy: 0.9785

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.73046875
Linear Weight Rank: 4031
Intra Cos: 0.5595522522926331
Inter Cos: 0.10632108896970749
Norm Quadratic Average: 85.42259216308594
Nearest Class Center Accuracy: 0.9805

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.372312545776367
Linear Weight Rank: 3670
Intra Cos: 0.7010002136230469
Inter Cos: 0.12544012069702148
Norm Quadratic Average: 39.344520568847656
Nearest Class Center Accuracy: 0.981

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.718390703201294
Linear Weight Rank: 10
Intra Cos: 0.7768692970275879
Inter Cos: 0.13201987743377686
Norm Quadratic Average: 22.40985107421875
Nearest Class Center Accuracy: 0.9815

Output Layer:
Intra Cos: 0.822020411491394
Inter Cos: 0.21112020313739777
Norm Quadratic Average: 11.247787475585938
Nearest Class Center Accuracy: 0.9805

