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_338327_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.027585506439209
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
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: 4.2131266593933105
Linear Weight Rank: 179
Intra Cos: 0.3606087565422058
Inter Cos: 0.006237193942070007
Norm Quadratic Average: 2.7131903171539307
Nearest Class Center Accuracy: 0.976375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0884463787078857
Linear Weight Rank: 4
Intra Cos: 0.7235950827598572
Inter Cos: 0.025326712056994438
Norm Quadratic Average: 3.375145435333252
Nearest Class Center Accuracy: 0.984875

Output Layer:
Intra Cos: 0.8296558856964111
Inter Cos: 0.027206916362047195
Norm Quadratic Average: 6.843721389770508
Nearest Class Center Accuracy: 0.9855

Test Set:
Average Loss: 0.18056766605377197
Accuracy: 0.985
NC1 Within Class Collapse: 2.426628828048706
NC2 Equinorm: Features: 0.04238808900117874, Weights: 0.016093367710709572
NC2 Equiangle: Features: 0.4340108235677083, Weights: 0.41184043884277344
NC3 Self-Duality: 0.020811572670936584
NC4 NCC Mismatch: 0.023499999999999965

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.027585506439209
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 4.2131266593933105
Linear Weight Rank: 179
Intra Cos: 0.3596859574317932
Inter Cos: 0.01629048027098179
Norm Quadratic Average: 2.725494861602783
Nearest Class Center Accuracy: 0.9705

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0884463787078857
Linear Weight Rank: 4
Intra Cos: 0.7185943126678467
Inter Cos: 0.04938356578350067
Norm Quadratic Average: 3.405941963195801
Nearest Class Center Accuracy: 0.9785

Output Layer:
Intra Cos: 0.8256855010986328
Inter Cos: 0.0547202043235302
Norm Quadratic Average: 6.8955512046813965
Nearest Class Center Accuracy: 0.9805

