Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.86224365234375
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.87454080581665
Linear Weight Rank: 178
Intra Cos: 0.03860130161046982
Inter Cos: -0.00674912054091692
Norm Quadratic Average: 3.5571508407592773
Nearest Class Center Accuracy: 0.6275

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0788979530334473
Linear Weight Rank: 4
Intra Cos: 0.1961745321750641
Inter Cos: -0.02977195754647255
Norm Quadratic Average: 1.962627649307251
Nearest Class Center Accuracy: 0.712375

Output Layer:
Intra Cos: 0.3293263912200928
Inter Cos: -0.044256847351789474
Norm Quadratic Average: 2.80971097946167
Nearest Class Center Accuracy: 0.71275

Test Set:
Average Loss: 0.728814567565918
Accuracy: 0.703
NC1 Within Class Collapse: 5.636255264282227
NC2 Equinorm: Features: 0.1518414467573166, Weights: 0.03993828594684601
NC2 Equiangle: Features: 0.2004724939664205, Weights: 0.05118751029173533
NC3 Self-Duality: 0.11278072744607925
NC4 NCC Mismatch: 0.09599999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.86224365234375
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.87454080581665
Linear Weight Rank: 178
Intra Cos: 0.034339334815740585
Inter Cos: -0.004397050477564335
Norm Quadratic Average: 3.5600481033325195
Nearest Class Center Accuracy: 0.6225

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.0788979530334473
Linear Weight Rank: 4
Intra Cos: 0.17278896272182465
Inter Cos: -0.011878707446157932
Norm Quadratic Average: 1.9465034008026123
Nearest Class Center Accuracy: 0.683

Output Layer:
Intra Cos: 0.2970687448978424
Inter Cos: -0.036097463220357895
Norm Quadratic Average: 2.7761738300323486
Nearest Class Center Accuracy: 0.687

