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_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.839521408081055
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: 7.904417991638184
Linear Weight Rank: 179
Intra Cos: 0.1852506846189499
Inter Cos: 0.0047055017203092575
Norm Quadratic Average: 4.958489894866943
Nearest Class Center Accuracy: 0.946

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8519937992095947
Linear Weight Rank: 4
Intra Cos: 0.6162460446357727
Inter Cos: 0.024569280445575714
Norm Quadratic Average: 6.11048698425293
Nearest Class Center Accuracy: 0.959375

Output Layer:
Intra Cos: 0.7789209485054016
Inter Cos: 0.031774215400218964
Norm Quadratic Average: 14.867552757263184
Nearest Class Center Accuracy: 0.9655

Test Set:
Average Loss: 0.09656021499633789
Accuracy: 0.978
NC1 Within Class Collapse: 3.4751875400543213
NC2 Equinorm: Features: 0.03740241378545761, Weights: 0.013403872027993202
NC2 Equiangle: Features: 0.43234411875406903, Weights: 0.39251287778218585
NC3 Self-Duality: 0.051256757229566574
NC4 NCC Mismatch: 0.04049999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.839521408081055
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: 7.904417991638184
Linear Weight Rank: 179
Intra Cos: 0.182987242937088
Inter Cos: 0.0026541631668806076
Norm Quadratic Average: 4.960753440856934
Nearest Class Center Accuracy: 0.95

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8519937992095947
Linear Weight Rank: 4
Intra Cos: 0.6026738882064819
Inter Cos: 0.014862662181258202
Norm Quadratic Average: 6.150502681732178
Nearest Class Center Accuracy: 0.9565

Output Layer:
Intra Cos: 0.7607386708259583
Inter Cos: 0.010649604722857475
Norm Quadratic Average: 14.959877967834473
Nearest Class Center Accuracy: 0.9585

