Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.0898356437683105
Linear Weight Rank: 16
Intra Cos: 0.014583898708224297
Inter Cos: 0.004829856567084789
Norm Quadratic Average: 3.993140459060669
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.270908355712891
Linear Weight Rank: 179
Intra Cos: 0.012497392483055592
Inter Cos: 0.00460564810782671
Norm Quadratic Average: 8.760544776916504
Nearest Class Center Accuracy: 0.466875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4504969120025635
Linear Weight Rank: 4
Intra Cos: 0.02262522652745247
Inter Cos: -0.0015256970655173063
Norm Quadratic Average: 9.343143463134766
Nearest Class Center Accuracy: 0.76625

Output Layer:
Intra Cos: 0.585898756980896
Inter Cos: -0.03328169137239456
Norm Quadratic Average: 3.5732502937316895
Nearest Class Center Accuracy: 0.935125

Test Set:
Average Loss: 1.114789779663086
Accuracy: 0.552
NC1 Within Class Collapse: 11.875842094421387
NC2 Equinorm: Features: 0.060736287385225296, Weights: 0.02541513182222843
NC2 Equiangle: Features: 0.23654433091481528, Weights: 0.034215485056241356
NC3 Self-Duality: 0.6507602334022522
NC4 NCC Mismatch: 0.32299999999999995

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.0898356437683105
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012289620935917
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.270908355712891
Linear Weight Rank: 179
Intra Cos: 0.013566562905907631
Inter Cos: 0.004533018916845322
Norm Quadratic Average: 8.725582122802734
Nearest Class Center Accuracy: 0.4695

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4504969120025635
Linear Weight Rank: 4
Intra Cos: 0.010504006408154964
Inter Cos: 0.0009045515907928348
Norm Quadratic Average: 9.400014877319336
Nearest Class Center Accuracy: 0.558

Output Layer:
Intra Cos: 0.16654925048351288
Inter Cos: 0.026598680764436722
Norm Quadratic Average: 3.4115540981292725
Nearest Class Center Accuracy: 0.5485

