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_265358_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.627842903137207
Linear Weight Rank: 16
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 6.690863609313965
Linear Weight Rank: 179
Intra Cos: 0.220517098903656
Inter Cos: 0.005803635809570551
Norm Quadratic Average: 4.190220832824707
Nearest Class Center Accuracy: 0.96525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.612058639526367
Linear Weight Rank: 4
Intra Cos: 0.6682566404342651
Inter Cos: 0.03084338828921318
Norm Quadratic Average: 5.081884860992432
Nearest Class Center Accuracy: 0.980875

Output Layer:
Intra Cos: 0.8168985843658447
Inter Cos: 0.026678655296564102
Norm Quadratic Average: 11.741271018981934
Nearest Class Center Accuracy: 0.983125

Test Set:
Average Loss: 0.11850414943695069
Accuracy: 0.9755
NC1 Within Class Collapse: 2.6468067169189453
NC2 Equinorm: Features: 0.028629126027226448, Weights: 0.02195248194038868
NC2 Equiangle: Features: 0.4315328200658162, Weights: 0.39538776874542236
NC3 Self-Duality: 0.03801191598176956
NC4 NCC Mismatch: 0.027000000000000024

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.627842903137207
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
Norm Quadratic Average: 3.9883358478546143
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 6.690863609313965
Linear Weight Rank: 179
Intra Cos: 0.21922719478607178
Inter Cos: 0.006807303987443447
Norm Quadratic Average: 4.198391437530518
Nearest Class Center Accuracy: 0.9635

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.612058639526367
Linear Weight Rank: 4
Intra Cos: 0.6656458973884583
Inter Cos: 0.034761056303977966
Norm Quadratic Average: 5.127727031707764
Nearest Class Center Accuracy: 0.9655

Output Layer:
Intra Cos: 0.8063879013061523
Inter Cos: 0.03727933019399643
Norm Quadratic Average: 11.832664489746094
Nearest Class Center Accuracy: 0.9705

