Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_846264_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.850136756896973
Linear Weight Rank: 16
Intra Cos: 0.07988917082548141
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.955125331878662
Linear Weight Rank: 179
Intra Cos: 0.18766926229000092
Inter Cos: 0.005536959040910006
Norm Quadratic Average: 4.938847541809082
Nearest Class Center Accuracy: 0.96325

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.862309455871582
Linear Weight Rank: 4
Intra Cos: 0.6307662725448608
Inter Cos: 0.030225476250052452
Norm Quadratic Average: 6.072606563568115
Nearest Class Center Accuracy: 0.973875

Output Layer:
Intra Cos: 0.7925070524215698
Inter Cos: 0.042109012603759766
Norm Quadratic Average: 14.84996509552002
Nearest Class Center Accuracy: 0.97425

Test Set:
Average Loss: 0.09746738862991333
Accuracy: 0.9795
NC1 Within Class Collapse: 2.888485908508301
NC2 Equinorm: Features: 0.03862323611974716, Weights: 0.016656827181577682
NC2 Equiangle: Features: 0.43430153528849286, Weights: 0.39786994457244873
NC3 Self-Duality: 0.0485125295817852
NC4 NCC Mismatch: 0.029000000000000026

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.850136756896973
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.955125331878662
Linear Weight Rank: 179
Intra Cos: 0.18486639857292175
Inter Cos: 0.0076599097810685635
Norm Quadratic Average: 4.947174549102783
Nearest Class Center Accuracy: 0.955

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.862309455871582
Linear Weight Rank: 4
Intra Cos: 0.6232694387435913
Inter Cos: 0.05288439616560936
Norm Quadratic Average: 6.132984638214111
Nearest Class Center Accuracy: 0.9665

Output Layer:
Intra Cos: 0.7827432751655579
Inter Cos: 0.06898458302021027
Norm Quadratic Average: 14.993170738220215
Nearest Class Center Accuracy: 0.9685

