Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.87414836883545
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.775579452514648
Linear Weight Rank: 179
Intra Cos: 0.03236813098192215
Inter Cos: -0.002856264589354396
Norm Quadratic Average: 5.255123138427734
Nearest Class Center Accuracy: 0.6175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6965086460113525
Linear Weight Rank: 4
Intra Cos: 0.12488269060850143
Inter Cos: -0.024119239300489426
Norm Quadratic Average: 3.2249879837036133
Nearest Class Center Accuracy: 0.739875

Output Layer:
Intra Cos: 0.3275383710861206
Inter Cos: -0.07078711688518524
Norm Quadratic Average: 4.034515857696533
Nearest Class Center Accuracy: 0.761625

Test Set:
Average Loss: 0.6398718166351318
Accuracy: 0.7295
NC1 Within Class Collapse: 5.4096856117248535
NC2 Equinorm: Features: 0.1264973133802414, Weights: 0.04470163956284523
NC2 Equiangle: Features: 0.18629475434621176, Weights: 0.03573231399059296
NC3 Self-Duality: 0.21548126637935638
NC4 NCC Mismatch: 0.10899999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.87414836883545
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: 8.775579452514648
Linear Weight Rank: 179
Intra Cos: 0.028702525421977043
Inter Cos: -0.002921516075730324
Norm Quadratic Average: 5.254620552062988
Nearest Class Center Accuracy: 0.615

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6965086460113525
Linear Weight Rank: 4
Intra Cos: 0.11117641627788544
Inter Cos: -0.012655274011194706
Norm Quadratic Average: 3.217240571975708
Nearest Class Center Accuracy: 0.7155

Output Layer:
Intra Cos: 0.296058714389801
Inter Cos: -0.049422647804021835
Norm Quadratic Average: 4.018370151519775
Nearest Class Center Accuracy: 0.7285

