Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.0641067028045654
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.2143163681030273
Linear Weight Rank: 178
Intra Cos: 0.03161120042204857
Inter Cos: -0.0045483652502298355
Norm Quadratic Average: 3.362980604171753
Nearest Class Center Accuracy: 0.60825

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.726447343826294
Linear Weight Rank: 4
Intra Cos: 0.19079743325710297
Inter Cos: -0.04812152311205864
Norm Quadratic Average: 4.134138584136963
Nearest Class Center Accuracy: 0.932

Output Layer:
Intra Cos: 0.6828673481941223
Inter Cos: -0.1796392947435379
Norm Quadratic Average: 3.6137452125549316
Nearest Class Center Accuracy: 0.956875

Test Set:
Average Loss: 0.5720362873077393
Accuracy: 0.765
NC1 Within Class Collapse: 3.1286959648132324
NC2 Equinorm: Features: 0.10624651610851288, Weights: 0.040858425199985504
NC2 Equiangle: Features: 0.11826982100804646, Weights: 0.021034027139345806
NC3 Self-Duality: 0.17501890659332275
NC4 NCC Mismatch: 0.05700000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.0641067028045654
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
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: 2.2143163681030273
Linear Weight Rank: 178
Intra Cos: 0.0295458622276783
Inter Cos: -0.0038327693473547697
Norm Quadratic Average: 3.3720016479492188
Nearest Class Center Accuracy: 0.596

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.726447343826294
Linear Weight Rank: 4
Intra Cos: 0.13387593626976013
Inter Cos: -0.015708614140748978
Norm Quadratic Average: 4.12631893157959
Nearest Class Center Accuracy: 0.765

Output Layer:
Intra Cos: 0.4591359794139862
Inter Cos: -0.05428539216518402
Norm Quadratic Average: 3.5367820262908936
Nearest Class Center Accuracy: 0.769

