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_314159_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.532390594482422
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584841698408127
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: 8.66792106628418
Linear Weight Rank: 179
Intra Cos: 0.1784917563199997
Inter Cos: 0.010118043050169945
Norm Quadratic Average: 5.3637309074401855
Nearest Class Center Accuracy: 0.9595

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.009880542755127
Linear Weight Rank: 4
Intra Cos: 0.6209739446640015
Inter Cos: 0.02782043069601059
Norm Quadratic Average: 6.6784772872924805
Nearest Class Center Accuracy: 0.977875

Output Layer:
Intra Cos: 0.8013536930084229
Inter Cos: 0.036928314715623856
Norm Quadratic Average: 16.714744567871094
Nearest Class Center Accuracy: 0.9785

Test Set:
Average Loss: 0.08449131035804748
Accuracy: 0.978
NC1 Within Class Collapse: 2.897714614868164
NC2 Equinorm: Features: 0.04431513696908951, Weights: 0.012697392143309116
NC2 Equiangle: Features: 0.43384567896525067, Weights: 0.3875651756922404
NC3 Self-Duality: 0.06043518707156181
NC4 NCC Mismatch: 0.026000000000000023

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.532390594482422
Linear Weight Rank: 16
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: 8.66792106628418
Linear Weight Rank: 179
Intra Cos: 0.17570896446704865
Inter Cos: 0.00948542170226574
Norm Quadratic Average: 5.371940612792969
Nearest Class Center Accuracy: 0.9545

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.009880542755127
Linear Weight Rank: 4
Intra Cos: 0.614514172077179
Inter Cos: 0.025177467614412308
Norm Quadratic Average: 6.741978645324707
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7895113825798035
Inter Cos: 0.029175791889429092
Norm Quadratic Average: 16.858665466308594
Nearest Class Center Accuracy: 0.9765

