Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.201879501342773
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.167705535888672
Linear Weight Rank: 180
Intra Cos: 0.030108818784356117
Inter Cos: -0.004105157218873501
Norm Quadratic Average: 12.233478546142578
Nearest Class Center Accuracy: 0.597625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6362264156341553
Linear Weight Rank: 4
Intra Cos: 0.04688859358429909
Inter Cos: -0.010500787757337093
Norm Quadratic Average: 12.661779403686523
Nearest Class Center Accuracy: 0.84425

Output Layer:
Intra Cos: 0.5769501328468323
Inter Cos: -0.13934293389320374
Norm Quadratic Average: 7.077868461608887
Nearest Class Center Accuracy: 0.982625

Test Set:
Average Loss: 0.6068999137878418
Accuracy: 0.769
NC1 Within Class Collapse: 4.816338062286377
NC2 Equinorm: Features: 0.11532234400510788, Weights: 0.039796046912670135
NC2 Equiangle: Features: 0.11590829491615295, Weights: 0.028885448972384136
NC3 Self-Duality: 0.4735092222690582
NC4 NCC Mismatch: 0.1915

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.201879501342773
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.167705535888672
Linear Weight Rank: 180
Intra Cos: 0.02686881273984909
Inter Cos: -0.0040844399482011795
Norm Quadratic Average: 12.238414764404297
Nearest Class Center Accuracy: 0.6

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6362264156341553
Linear Weight Rank: 4
Intra Cos: 0.03575500473380089
Inter Cos: -0.005998929496854544
Norm Quadratic Average: 12.677985191345215
Nearest Class Center Accuracy: 0.7295

Output Layer:
Intra Cos: 0.3719940185546875
Inter Cos: -0.06851749122142792
Norm Quadratic Average: 6.954107284545898
Nearest Class Center Accuracy: 0.7645

