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_0.005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.228707790374756
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: 7.27577543258667
Linear Weight Rank: 179
Intra Cos: 0.20498506724834442
Inter Cos: 0.006168856285512447
Norm Quadratic Average: 4.536782741546631
Nearest Class Center Accuracy: 0.9625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7339401245117188
Linear Weight Rank: 4
Intra Cos: 0.6565594673156738
Inter Cos: 0.03177402913570404
Norm Quadratic Average: 5.547015190124512
Nearest Class Center Accuracy: 0.98075

Output Layer:
Intra Cos: 0.8147848844528198
Inter Cos: 0.028382280841469765
Norm Quadratic Average: 13.163244247436523
Nearest Class Center Accuracy: 0.983

Test Set:
Average Loss: 0.10847400712966919
Accuracy: 0.975
NC1 Within Class Collapse: 2.6688826084136963
NC2 Equinorm: Features: 0.02811325155198574, Weights: 0.02237754501402378
NC2 Equiangle: Features: 0.43161332607269287, Weights: 0.3931668996810913
NC3 Self-Duality: 0.04256483167409897
NC4 NCC Mismatch: 0.027000000000000024

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.228707790374756
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: 7.27577543258667
Linear Weight Rank: 179
Intra Cos: 0.20480793714523315
Inter Cos: 0.005683204159140587
Norm Quadratic Average: 4.544333457946777
Nearest Class Center Accuracy: 0.9625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7339401245117188
Linear Weight Rank: 4
Intra Cos: 0.65414959192276
Inter Cos: 0.03306275233626366
Norm Quadratic Average: 5.59712028503418
Nearest Class Center Accuracy: 0.965

Output Layer:
Intra Cos: 0.8036765456199646
Inter Cos: 0.03659236058592796
Norm Quadratic Average: 13.267752647399902
Nearest Class Center Accuracy: 0.97

