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_265358_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.853424072265625
Linear Weight Rank: 16
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
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: 8.864338874816895
Linear Weight Rank: 179
Intra Cos: 0.17590779066085815
Inter Cos: 0.007008343935012817
Norm Quadratic Average: 5.4810566902160645
Nearest Class Center Accuracy: 0.956

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.071706771850586
Linear Weight Rank: 4
Intra Cos: 0.6261596083641052
Inter Cos: 0.033754102885723114
Norm Quadratic Average: 6.960928916931152
Nearest Class Center Accuracy: 0.9805

Output Layer:
Intra Cos: 0.8102664351463318
Inter Cos: 0.032962411642074585
Norm Quadratic Average: 17.68634033203125
Nearest Class Center Accuracy: 0.982375

Test Set:
Average Loss: 0.08841576051712036
Accuracy: 0.9755
NC1 Within Class Collapse: 2.732362985610962
NC2 Equinorm: Features: 0.026677699759602547, Weights: 0.023379294201731682
NC2 Equiangle: Features: 0.43202733993530273, Weights: 0.3875867525736491
NC3 Self-Duality: 0.05455150455236435
NC4 NCC Mismatch: 0.023499999999999965

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.853424072265625
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
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: 8.864338874816895
Linear Weight Rank: 179
Intra Cos: 0.17815151810646057
Inter Cos: 0.0035080069210380316
Norm Quadratic Average: 5.486963272094727
Nearest Class Center Accuracy: 0.9545

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.071706771850586
Linear Weight Rank: 4
Intra Cos: 0.6233884692192078
Inter Cos: 0.028765056282281876
Norm Quadratic Average: 7.0229692459106445
Nearest Class Center Accuracy: 0.965

Output Layer:
Intra Cos: 0.7973199486732483
Inter Cos: 0.034812670201063156
Norm Quadratic Average: 17.831579208374023
Nearest Class Center Accuracy: 0.969

