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_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.084029197692871
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: 8.147664070129395
Linear Weight Rank: 179
Intra Cos: 0.02713542990386486
Inter Cos: -0.004272978752851486
Norm Quadratic Average: 13.909462928771973
Nearest Class Center Accuracy: 0.589375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7875850200653076
Linear Weight Rank: 4
Intra Cos: 0.043375156819820404
Inter Cos: -0.0082531264051795
Norm Quadratic Average: 14.322087287902832
Nearest Class Center Accuracy: 0.796125

Output Layer:
Intra Cos: 0.5663696527481079
Inter Cos: -0.09333924949169159
Norm Quadratic Average: 7.675647735595703
Nearest Class Center Accuracy: 0.9785

Test Set:
Average Loss: 0.6312140884399414
Accuracy: 0.769
NC1 Within Class Collapse: 5.421117782592773
NC2 Equinorm: Features: 0.13996124267578125, Weights: 0.05020754039287567
NC2 Equiangle: Features: 0.1394702990849813, Weights: 0.03454176584879557
NC3 Self-Duality: 0.5935048460960388
NC4 NCC Mismatch: 0.254

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.084029197692871
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: 8.147664070129395
Linear Weight Rank: 179
Intra Cos: 0.026187777519226074
Inter Cos: -0.003667055396363139
Norm Quadratic Average: 13.967182159423828
Nearest Class Center Accuracy: 0.5805

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7875850200653076
Linear Weight Rank: 4
Intra Cos: 0.03237609192728996
Inter Cos: -0.003420100547373295
Norm Quadratic Average: 14.360395431518555
Nearest Class Center Accuracy: 0.6855

Output Layer:
Intra Cos: 0.3734806478023529
Inter Cos: -0.043348051607608795
Norm Quadratic Average: 7.524167537689209
Nearest Class Center Accuracy: 0.7595

