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_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.271566867828369
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: 2.5733048915863037
Linear Weight Rank: 174
Intra Cos: 0.6653556823730469
Inter Cos: 0.00726936012506485
Norm Quadratic Average: 1.7119910717010498
Nearest Class Center Accuracy: 0.975

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.5601236820220947
Linear Weight Rank: 3
Intra Cos: 0.7434710264205933
Inter Cos: 0.011848559603095055
Norm Quadratic Average: 2.2739973068237305
Nearest Class Center Accuracy: 0.978875

Output Layer:
Intra Cos: 0.8246662616729736
Inter Cos: 0.009191839024424553
Norm Quadratic Average: 3.911119222640991
Nearest Class Center Accuracy: 0.981875

Test Set:
Average Loss: 0.3123292751312256
Accuracy: 0.9845
NC1 Within Class Collapse: 4.506915092468262
NC2 Equinorm: Features: 0.03223847970366478, Weights: 0.012140350416302681
NC2 Equiangle: Features: 0.43868382771809894, Weights: 0.42550750573476154
NC3 Self-Duality: 0.007888835854828358
NC4 NCC Mismatch: 0.02400000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.271566867828369
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: 2.5733048915863037
Linear Weight Rank: 174
Intra Cos: 0.6639165878295898
Inter Cos: 0.028678931295871735
Norm Quadratic Average: 1.7263706922531128
Nearest Class Center Accuracy: 0.969

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.5601236820220947
Linear Weight Rank: 3
Intra Cos: 0.736082911491394
Inter Cos: 0.03447875753045082
Norm Quadratic Average: 2.289682388305664
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.8287580013275146
Inter Cos: 0.03772440925240517
Norm Quadratic Average: 3.933563232421875
Nearest Class Center Accuracy: 0.9775

