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_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.652542114257812
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: 8.6672945022583
Linear Weight Rank: 179
Intra Cos: 0.17869384586811066
Inter Cos: 0.006959233433008194
Norm Quadratic Average: 5.363774299621582
Nearest Class Center Accuracy: 0.957

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.029260635375977
Linear Weight Rank: 4
Intra Cos: 0.629801332950592
Inter Cos: 0.033695317804813385
Norm Quadratic Average: 6.773172378540039
Nearest Class Center Accuracy: 0.98075

Output Layer:
Intra Cos: 0.8107207417488098
Inter Cos: 0.03259005397558212
Norm Quadratic Average: 17.069133758544922
Nearest Class Center Accuracy: 0.98225

Test Set:
Average Loss: 0.09046366834640503
Accuracy: 0.9755
NC1 Within Class Collapse: 2.7285449504852295
NC2 Equinorm: Features: 0.026816351339221, Weights: 0.023240257054567337
NC2 Equiangle: Features: 0.4319881598154704, Weights: 0.3882475694020589
NC3 Self-Duality: 0.053103916347026825
NC4 NCC Mismatch: 0.023499999999999965

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.652542114257812
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: 8.6672945022583
Linear Weight Rank: 179
Intra Cos: 0.18067416548728943
Inter Cos: 0.0036630271933972836
Norm Quadratic Average: 5.369845390319824
Nearest Class Center Accuracy: 0.957

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.029260635375977
Linear Weight Rank: 4
Intra Cos: 0.6274433135986328
Inter Cos: 0.029102569445967674
Norm Quadratic Average: 6.833679676055908
Nearest Class Center Accuracy: 0.965

Output Layer:
Intra Cos: 0.7978906631469727
Inter Cos: 0.03483434021472931
Norm Quadratic Average: 17.20885467529297
Nearest Class Center Accuracy: 0.969

