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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.796502113342285
Linear Weight Rank: 16
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: 8.891402244567871
Linear Weight Rank: 179
Intra Cos: 0.17290344834327698
Inter Cos: 0.006092585623264313
Norm Quadratic Average: 5.497422695159912
Nearest Class Center Accuracy: 0.959375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.061032772064209
Linear Weight Rank: 4
Intra Cos: 0.6111955046653748
Inter Cos: 0.027591681107878685
Norm Quadratic Average: 6.926100254058838
Nearest Class Center Accuracy: 0.97275

Output Layer:
Intra Cos: 0.7902100086212158
Inter Cos: 0.040144383907318115
Norm Quadratic Average: 17.616270065307617
Nearest Class Center Accuracy: 0.973625

Test Set:
Average Loss: 0.08636189985275268
Accuracy: 0.979
NC1 Within Class Collapse: 2.9760994911193848
NC2 Equinorm: Features: 0.0385378822684288, Weights: 0.01660860888659954
NC2 Equiangle: Features: 0.434495488802592, Weights: 0.3943134943644206
NC3 Self-Duality: 0.05556625500321388
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.796502113342285
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: 8.891402244567871
Linear Weight Rank: 179
Intra Cos: 0.17019309103488922
Inter Cos: 0.006708451081067324
Norm Quadratic Average: 5.50536584854126
Nearest Class Center Accuracy: 0.9525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.061032772064209
Linear Weight Rank: 4
Intra Cos: 0.6036161184310913
Inter Cos: 0.049797624349594116
Norm Quadratic Average: 6.994685649871826
Nearest Class Center Accuracy: 0.964

Output Layer:
Intra Cos: 0.7803946733474731
Inter Cos: 0.06706684082746506
Norm Quadratic Average: 17.790660858154297
Nearest Class Center Accuracy: 0.967

