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_338327_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.880996704101562
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.953922271728516
Linear Weight Rank: 180
Intra Cos: 0.1767769157886505
Inter Cos: 0.002552899532020092
Norm Quadratic Average: 5.492997646331787
Nearest Class Center Accuracy: 0.956625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.098237991333008
Linear Weight Rank: 4
Intra Cos: 0.633744478225708
Inter Cos: 0.024223795160651207
Norm Quadratic Average: 6.930197238922119
Nearest Class Center Accuracy: 0.982125

Output Layer:
Intra Cos: 0.8163439631462097
Inter Cos: 0.03571008890867233
Norm Quadratic Average: 17.724876403808594
Nearest Class Center Accuracy: 0.982375

Test Set:
Average Loss: 0.08513657069206237
Accuracy: 0.983
NC1 Within Class Collapse: 2.791071891784668
NC2 Equinorm: Features: 0.04483680799603462, Weights: 0.01709328219294548
NC2 Equiangle: Features: 0.4344615538914998, Weights: 0.3878854115804036
NC3 Self-Duality: 0.06077617034316063
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.880996704101562
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.953922271728516
Linear Weight Rank: 180
Intra Cos: 0.1741570085287094
Inter Cos: 0.007260182872414589
Norm Quadratic Average: 5.498768329620361
Nearest Class Center Accuracy: 0.951

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.098237991333008
Linear Weight Rank: 4
Intra Cos: 0.6277190446853638
Inter Cos: 0.048137813806533813
Norm Quadratic Average: 7.001728534698486
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.8047134280204773
Inter Cos: 0.06466814130544662
Norm Quadratic Average: 17.90377426147461
Nearest Class Center Accuracy: 0.9755

