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_314159_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.006829261779785
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.070656776428223
Linear Weight Rank: 179
Intra Cos: 0.027187589555978775
Inter Cos: -0.004320985171943903
Norm Quadratic Average: 13.776668548583984
Nearest Class Center Accuracy: 0.588875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.775956630706787
Linear Weight Rank: 4
Intra Cos: 0.0437302403151989
Inter Cos: -0.008352904580533504
Norm Quadratic Average: 14.192449569702148
Nearest Class Center Accuracy: 0.799625

Output Layer:
Intra Cos: 0.5667202472686768
Inter Cos: -0.09291182458400726
Norm Quadratic Average: 7.6355085372924805
Nearest Class Center Accuracy: 0.97875

Test Set:
Average Loss: 0.6278314208984375
Accuracy: 0.769
NC1 Within Class Collapse: 5.393437385559082
NC2 Equinorm: Features: 0.13941526412963867, Weights: 0.05015847086906433
NC2 Equiangle: Features: 0.13963375488917032, Weights: 0.03414240479469299
NC3 Self-Duality: 0.5861702561378479
NC4 NCC Mismatch: 0.25149999999999995

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.006829261779785
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
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: 8.070656776428223
Linear Weight Rank: 179
Intra Cos: 0.026177681982517242
Inter Cos: -0.0037256614305078983
Norm Quadratic Average: 13.83393383026123
Nearest Class Center Accuracy: 0.582

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.775956630706787
Linear Weight Rank: 4
Intra Cos: 0.032593414187431335
Inter Cos: -0.0034716771915555
Norm Quadratic Average: 14.23185920715332
Nearest Class Center Accuracy: 0.6865

Output Layer:
Intra Cos: 0.37335821986198425
Inter Cos: -0.04421522095799446
Norm Quadratic Average: 7.484035491943359
Nearest Class Center Accuracy: 0.759

