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_979323_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0515248775482178
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.001758486032485962
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: 3.3005764484405518
Linear Weight Rank: 177
Intra Cos: 0.4840039908885956
Inter Cos: 0.00748603418469429
Norm Quadratic Average: 2.178605318069458
Nearest Class Center Accuracy: 0.966625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.8543896675109863
Linear Weight Rank: 4
Intra Cos: 0.7142400145530701
Inter Cos: 0.02128675952553749
Norm Quadratic Average: 2.852731227874756
Nearest Class Center Accuracy: 0.97225

Output Layer:
Intra Cos: 0.8107657432556152
Inter Cos: 0.016038738191127777
Norm Quadratic Average: 5.387040138244629
Nearest Class Center Accuracy: 0.976625

Test Set:
Average Loss: 0.22688437747955323
Accuracy: 0.987
NC1 Within Class Collapse: 3.0230212211608887
NC2 Equinorm: Features: 0.03058505430817604, Weights: 0.010367287322878838
NC2 Equiangle: Features: 0.4349399407704671, Weights: 0.415219783782959
NC3 Self-Duality: 0.014868784695863724
NC4 NCC Mismatch: 0.02849999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0515248775482178
Linear Weight Rank: 16
Intra Cos: 0.08033028244972229
Inter Cos: 0.003312898799777031
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: 3.3005764484405518
Linear Weight Rank: 177
Intra Cos: 0.4788312315940857
Inter Cos: 0.006205495446920395
Norm Quadratic Average: 2.191532611846924
Nearest Class Center Accuracy: 0.964

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.8543896675109863
Linear Weight Rank: 4
Intra Cos: 0.7037872672080994
Inter Cos: 0.014025943353772163
Norm Quadratic Average: 2.8725745677948
Nearest Class Center Accuracy: 0.9695

Output Layer:
Intra Cos: 0.8127083778381348
Inter Cos: 0.019771086052060127
Norm Quadratic Average: 5.41878604888916
Nearest Class Center Accuracy: 0.9775

