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_338327_weight_decay_0.1.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.7521175146102905
Linear Weight Rank: 11
Intra Cos: 0.07988917827606201
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: 2.0158321857452393
Linear Weight Rank: 144
Intra Cos: 0.7351776957511902
Inter Cos: 0.02001214399933815
Norm Quadratic Average: 1.3410981893539429
Nearest Class Center Accuracy: 0.979375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.098224401473999
Linear Weight Rank: 3
Intra Cos: 0.7766439318656921
Inter Cos: 0.02349948137998581
Norm Quadratic Average: 1.5450576543807983
Nearest Class Center Accuracy: 0.9825

Output Layer:
Intra Cos: 0.8310678601264954
Inter Cos: 0.02287294529378414
Norm Quadratic Average: 2.21948504447937
Nearest Class Center Accuracy: 0.9795

Test Set:
Average Loss: 0.5387370471954346
Accuracy: 0.9745
NC1 Within Class Collapse: 11.951355934143066
NC2 Equinorm: Features: 0.04884377121925354, Weights: 0.02274133265018463
NC2 Equiangle: Features: 0.4420613447825114, Weights: 0.4390100638071696
NC3 Self-Duality: 0.002935342723503709
NC4 NCC Mismatch: 0.03849999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.7521175146102905
Linear Weight Rank: 11
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 2.0158321857452393
Linear Weight Rank: 144
Intra Cos: 0.7390486598014832
Inter Cos: 0.045212630182504654
Norm Quadratic Average: 1.3536708354949951
Nearest Class Center Accuracy: 0.972

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.098224401473999
Linear Weight Rank: 3
Intra Cos: 0.7736092805862427
Inter Cos: 0.049717895686626434
Norm Quadratic Average: 1.5555528402328491
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.8357328772544861
Inter Cos: 0.05026915296912193
Norm Quadratic Average: 2.2312474250793457
Nearest Class Center Accuracy: 0.9785

