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_338327_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.060866594314575
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
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: 3.3067281246185303
Linear Weight Rank: 178
Intra Cos: 0.49020442366600037
Inter Cos: 0.009342333301901817
Norm Quadratic Average: 2.174081563949585
Nearest Class Center Accuracy: 0.978875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.8564670085906982
Linear Weight Rank: 4
Intra Cos: 0.7381610870361328
Inter Cos: 0.025708137080073357
Norm Quadratic Average: 2.839077949523926
Nearest Class Center Accuracy: 0.985125

Output Layer:
Intra Cos: 0.8342137336730957
Inter Cos: 0.026160573586821556
Norm Quadratic Average: 5.380068778991699
Nearest Class Center Accuracy: 0.985125

Test Set:
Average Loss: 0.2244274926185608
Accuracy: 0.988
NC1 Within Class Collapse: 2.584315776824951
NC2 Equinorm: Features: 0.04209335148334503, Weights: 0.015763163566589355
NC2 Equiangle: Features: 0.43559515476226807, Weights: 0.4177763859430949
NC3 Self-Duality: 0.013110863044857979
NC4 NCC Mismatch: 0.02300000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.060866594314575
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 3.3067281246185303
Linear Weight Rank: 178
Intra Cos: 0.49484777450561523
Inter Cos: 0.026036826893687248
Norm Quadratic Average: 2.1885948181152344
Nearest Class Center Accuracy: 0.9735

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.8564670085906982
Linear Weight Rank: 4
Intra Cos: 0.7357701063156128
Inter Cos: 0.05088317394256592
Norm Quadratic Average: 2.8629536628723145
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.8348805904388428
Inter Cos: 0.05475601553916931
Norm Quadratic Average: 5.41695499420166
Nearest Class Center Accuracy: 0.9815

