Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.213632583618164
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222442723810673
Norm Quadratic Average: 3.9938886165618896
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.187088966369629
Linear Weight Rank: 180
Intra Cos: 0.02535911276936531
Inter Cos: -0.0046317121013998985
Norm Quadratic Average: 13.976945877075195
Nearest Class Center Accuracy: 0.5915

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.966360092163086
Linear Weight Rank: 4
Intra Cos: 0.04035741463303566
Inter Cos: -0.009207893162965775
Norm Quadratic Average: 14.459715843200684
Nearest Class Center Accuracy: 0.823875

Output Layer:
Intra Cos: 0.5697150826454163
Inter Cos: -0.12048713862895966
Norm Quadratic Average: 8.069650650024414
Nearest Class Center Accuracy: 0.98725

Test Set:
Average Loss: 0.6314058227539062
Accuracy: 0.766
NC1 Within Class Collapse: 5.0982561111450195
NC2 Equinorm: Features: 0.13071075081825256, Weights: 0.04073328152298927
NC2 Equiangle: Features: 0.14037798841794333, Weights: 0.03077886253595352
NC3 Self-Duality: 0.5225512981414795
NC4 NCC Mismatch: 0.21150000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.213632583618164
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.00454972218722105
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.187088966369629
Linear Weight Rank: 180
Intra Cos: 0.02321108803153038
Inter Cos: -0.0032872515730559826
Norm Quadratic Average: 13.970243453979492
Nearest Class Center Accuracy: 0.6005

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.966360092163086
Linear Weight Rank: 4
Intra Cos: 0.02972261607646942
Inter Cos: -0.00458163907751441
Norm Quadratic Average: 14.459662437438965
Nearest Class Center Accuracy: 0.715

Output Layer:
Intra Cos: 0.36564040184020996
Inter Cos: -0.057774867862463
Norm Quadratic Average: 7.989808559417725
Nearest Class Center Accuracy: 0.764

