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_0.04.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5479495525360107
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: 2.8341922760009766
Linear Weight Rank: 176
Intra Cos: 0.5948960781097412
Inter Cos: 0.012501965276896954
Norm Quadratic Average: 1.8813586235046387
Nearest Class Center Accuracy: 0.98

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.689096689224243
Linear Weight Rank: 4
Intra Cos: 0.7498866319656372
Inter Cos: 0.019342781975865364
Norm Quadratic Average: 2.5062344074249268
Nearest Class Center Accuracy: 0.985375

Output Layer:
Intra Cos: 0.8398451805114746
Inter Cos: 0.01703563518822193
Norm Quadratic Average: 4.506453514099121
Nearest Class Center Accuracy: 0.985375

Test Set:
Average Loss: 0.26669792270660403
Accuracy: 0.987
NC1 Within Class Collapse: 3.1792030334472656
NC2 Equinorm: Features: 0.0398566909134388, Weights: 0.01502092182636261
NC2 Equiangle: Features: 0.43774553140004474, Weights: 0.4222087065378825
NC3 Self-Duality: 0.009026340208947659
NC4 NCC Mismatch: 0.025499999999999967

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5479495525360107
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: 2.8341922760009766
Linear Weight Rank: 176
Intra Cos: 0.6009687781333923
Inter Cos: 0.03499935567378998
Norm Quadratic Average: 1.8966816663742065
Nearest Class Center Accuracy: 0.972

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.689096689224243
Linear Weight Rank: 4
Intra Cos: 0.7456600666046143
Inter Cos: 0.0434708409011364
Norm Quadratic Average: 2.526749610900879
Nearest Class Center Accuracy: 0.9785

Output Layer:
Intra Cos: 0.8339897394180298
Inter Cos: 0.0431266650557518
Norm Quadratic Average: 4.5358171463012695
Nearest Class Center Accuracy: 0.9825

