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_0.04.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5477445125579834
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: 2.835158109664917
Linear Weight Rank: 176
Intra Cos: 0.5998682379722595
Inter Cos: 0.013726560398936272
Norm Quadratic Average: 1.8826059103012085
Nearest Class Center Accuracy: 0.981625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.691783905029297
Linear Weight Rank: 4
Intra Cos: 0.7494704127311707
Inter Cos: 0.021093282848596573
Norm Quadratic Average: 2.5110695362091064
Nearest Class Center Accuracy: 0.9845

Output Layer:
Intra Cos: 0.8334473371505737
Inter Cos: 0.019615966826677322
Norm Quadratic Average: 4.512241840362549
Nearest Class Center Accuracy: 0.986125

Test Set:
Average Loss: 0.27116573619842527
Accuracy: 0.987
NC1 Within Class Collapse: 3.3076109886169434
NC2 Equinorm: Features: 0.03660718724131584, Weights: 0.013495353050529957
NC2 Equiangle: Features: 0.4365907510121663, Weights: 0.41752652327219647
NC3 Self-Duality: 0.009312093257904053
NC4 NCC Mismatch: 0.026499999999999968

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5477445125579834
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: 2.835158109664917
Linear Weight Rank: 176
Intra Cos: 0.5974906086921692
Inter Cos: 0.03598485514521599
Norm Quadratic Average: 1.8976244926452637
Nearest Class Center Accuracy: 0.9735

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.691783905029297
Linear Weight Rank: 4
Intra Cos: 0.7494009137153625
Inter Cos: 0.046230994164943695
Norm Quadratic Average: 2.531886577606201
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.835220217704773
Inter Cos: 0.04631572961807251
Norm Quadratic Average: 4.5429606437683105
Nearest Class Center Accuracy: 0.982

