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_314159_weight_decay_0.1.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.7523308992385864
Linear Weight Rank: 11
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584841698408127
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: 2.0162806510925293
Linear Weight Rank: 144
Intra Cos: 0.733994722366333
Inter Cos: 0.021359048783779144
Norm Quadratic Average: 1.3412801027297974
Nearest Class Center Accuracy: 0.980125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.09846830368042
Linear Weight Rank: 3
Intra Cos: 0.7797691226005554
Inter Cos: 0.02320190519094467
Norm Quadratic Average: 1.54538893699646
Nearest Class Center Accuracy: 0.983375

Output Layer:
Intra Cos: 0.8348945379257202
Inter Cos: 0.02190862037241459
Norm Quadratic Average: 2.220186948776245
Nearest Class Center Accuracy: 0.98225

Test Set:
Average Loss: 0.5384445667266846
Accuracy: 0.975
NC1 Within Class Collapse: 13.573450088500977
NC2 Equinorm: Features: 0.045931439846754074, Weights: 0.022315634414553642
NC2 Equiangle: Features: 0.44221965471903485, Weights: 0.43923946221669513
NC3 Self-Duality: 0.0027794779743999243
NC4 NCC Mismatch: 0.040000000000000036

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.7523308992385864
Linear Weight Rank: 11
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
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: 2.0162806510925293
Linear Weight Rank: 144
Intra Cos: 0.7390362620353699
Inter Cos: 0.046549227088689804
Norm Quadratic Average: 1.3538683652877808
Nearest Class Center Accuracy: 0.974

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.09846830368042
Linear Weight Rank: 3
Intra Cos: 0.7775065302848816
Inter Cos: 0.04882393032312393
Norm Quadratic Average: 1.5564086437225342
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.835236132144928
Inter Cos: 0.048368021845817566
Norm Quadratic Average: 2.2327210903167725
Nearest Class Center Accuracy: 0.9795

