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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.8926420211792
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: 9.027376174926758
Linear Weight Rank: 179
Intra Cos: 0.17365635931491852
Inter Cos: 0.0100106755271554
Norm Quadratic Average: 5.578089237213135
Nearest Class Center Accuracy: 0.95875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.08773946762085
Linear Weight Rank: 4
Intra Cos: 0.613905668258667
Inter Cos: 0.027444591745734215
Norm Quadratic Average: 7.020503997802734
Nearest Class Center Accuracy: 0.977625

Output Layer:
Intra Cos: 0.8004897832870483
Inter Cos: 0.03710801154375076
Norm Quadratic Average: 17.837316513061523
Nearest Class Center Accuracy: 0.97825

Test Set:
Average Loss: 0.08067912888526917
Accuracy: 0.978
NC1 Within Class Collapse: 2.926815986633301
NC2 Equinorm: Features: 0.04461232200264931, Weights: 0.012526384554803371
NC2 Equiangle: Features: 0.4339276949564616, Weights: 0.3860789934794108
NC3 Self-Duality: 0.0633612722158432
NC4 NCC Mismatch: 0.026000000000000023

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.8926420211792
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: 9.027376174926758
Linear Weight Rank: 179
Intra Cos: 0.17093734443187714
Inter Cos: 0.009466806426644325
Norm Quadratic Average: 5.586005687713623
Nearest Class Center Accuracy: 0.9525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.08773946762085
Linear Weight Rank: 4
Intra Cos: 0.6074617505073547
Inter Cos: 0.024535123258829117
Norm Quadratic Average: 7.086909294128418
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7885047793388367
Inter Cos: 0.029262013733386993
Norm Quadratic Average: 17.991973876953125
Nearest Class Center Accuracy: 0.9765

