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_265358_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.038560390472412
Linear Weight Rank: 16
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
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: 4.210261821746826
Linear Weight Rank: 178
Intra Cos: 0.35972124338150024
Inter Cos: 0.0025533693842589855
Norm Quadratic Average: 2.721778631210327
Nearest Class Center Accuracy: 0.97675

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0886363983154297
Linear Weight Rank: 4
Intra Cos: 0.7168367505073547
Inter Cos: 0.01881052926182747
Norm Quadratic Average: 3.40568470954895
Nearest Class Center Accuracy: 0.9825

Output Layer:
Intra Cos: 0.8277513980865479
Inter Cos: 0.016078660264611244
Norm Quadratic Average: 6.897517204284668
Nearest Class Center Accuracy: 0.98425

Test Set:
Average Loss: 0.18312035846710206
Accuracy: 0.984
NC1 Within Class Collapse: 2.5997753143310547
NC2 Equinorm: Features: 0.031946342438459396, Weights: 0.018451474606990814
NC2 Equiangle: Features: 0.4325644175211589, Weights: 0.4062489668528239
NC3 Self-Duality: 0.018834369257092476
NC4 NCC Mismatch: 0.024499999999999966

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.038560390472412
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
Norm Quadratic Average: 3.9883358478546143
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 4.210261821746826
Linear Weight Rank: 178
Intra Cos: 0.3542385399341583
Inter Cos: 0.01824740134179592
Norm Quadratic Average: 2.733797788619995
Nearest Class Center Accuracy: 0.9705

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0886363983154297
Linear Weight Rank: 4
Intra Cos: 0.715889036655426
Inter Cos: 0.044149383902549744
Norm Quadratic Average: 3.4358818531036377
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.8224762082099915
Inter Cos: 0.044092800468206406
Norm Quadratic Average: 6.94757604598999
Nearest Class Center Accuracy: 0.9785

