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_846264_weight_decay_0.1.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.750784993171692
Linear Weight Rank: 11
Intra Cos: 0.07988917082548141
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.0151989459991455
Linear Weight Rank: 144
Intra Cos: 0.7296200394630432
Inter Cos: 0.02186712436378002
Norm Quadratic Average: 1.3404446840286255
Nearest Class Center Accuracy: 0.97975

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.0976924896240234
Linear Weight Rank: 3
Intra Cos: 0.7694810032844543
Inter Cos: 0.025726035237312317
Norm Quadratic Average: 1.5446664094924927
Nearest Class Center Accuracy: 0.980125

Output Layer:
Intra Cos: 0.8294278383255005
Inter Cos: 0.023844387382268906
Norm Quadratic Average: 2.218294620513916
Nearest Class Center Accuracy: 0.979125

Test Set:
Average Loss: 0.5400423660278321
Accuracy: 0.9755
NC1 Within Class Collapse: 12.811882972717285
NC2 Equinorm: Features: 0.04733215272426605, Weights: 0.022546619176864624
NC2 Equiangle: Features: 0.4422446091969808, Weights: 0.4392642180124919
NC3 Self-Duality: 0.003300366923213005
NC4 NCC Mismatch: 0.03849999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.750784993171692
Linear Weight Rank: 11
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.0151989459991455
Linear Weight Rank: 144
Intra Cos: 0.7371872067451477
Inter Cos: 0.047346968203783035
Norm Quadratic Average: 1.3527592420578003
Nearest Class Center Accuracy: 0.9745

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.0976924896240234
Linear Weight Rank: 3
Intra Cos: 0.7668772339820862
Inter Cos: 0.05224829912185669
Norm Quadratic Average: 1.5553054809570312
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.8264164328575134
Inter Cos: 0.05143268406391144
Norm Quadratic Average: 2.2296853065490723
Nearest Class Center Accuracy: 0.978

