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_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.865477561950684
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: 8.913467407226562
Linear Weight Rank: 179
Intra Cos: 0.16996321082115173
Inter Cos: 0.0047826385125517845
Norm Quadratic Average: 5.568539142608643
Nearest Class Center Accuracy: 0.94375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.066246032714844
Linear Weight Rank: 4
Intra Cos: 0.5968385338783264
Inter Cos: 0.02252965420484543
Norm Quadratic Average: 7.048659324645996
Nearest Class Center Accuracy: 0.9595

Output Layer:
Intra Cos: 0.7771562337875366
Inter Cos: 0.03138744831085205
Norm Quadratic Average: 17.90660858154297
Nearest Class Center Accuracy: 0.9655

Test Set:
Average Loss: 0.08446093153953552
Accuracy: 0.9755
NC1 Within Class Collapse: 3.5824460983276367
NC2 Equinorm: Features: 0.03861260786652565, Weights: 0.01377936266362667
NC2 Equiangle: Features: 0.4325760205586751, Weights: 0.38867437839508057
NC3 Self-Duality: 0.058703817427158356
NC4 NCC Mismatch: 0.04300000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.865477561950684
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: 8.913467407226562
Linear Weight Rank: 179
Intra Cos: 0.16775813698768616
Inter Cos: 0.002834487706422806
Norm Quadratic Average: 5.569429397583008
Nearest Class Center Accuracy: 0.9485

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.066246032714844
Linear Weight Rank: 4
Intra Cos: 0.5837093591690063
Inter Cos: 0.013434140011668205
Norm Quadratic Average: 7.093973636627197
Nearest Class Center Accuracy: 0.955

Output Layer:
Intra Cos: 0.7571422457695007
Inter Cos: 0.01002056896686554
Norm Quadratic Average: 18.01995086669922
Nearest Class Center Accuracy: 0.956

