Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.73361587524414
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: 8.743768692016602
Linear Weight Rank: 179
Intra Cos: 0.030662406235933304
Inter Cos: -0.0056425402872264385
Norm Quadratic Average: 5.247099876403809
Nearest Class Center Accuracy: 0.60875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.571547746658325
Linear Weight Rank: 4
Intra Cos: 0.12445230036973953
Inter Cos: -0.02048671990633011
Norm Quadratic Average: 3.1203479766845703
Nearest Class Center Accuracy: 0.732875

Output Layer:
Intra Cos: 0.3489876389503479
Inter Cos: -0.0692899078130722
Norm Quadratic Average: 3.7701826095581055
Nearest Class Center Accuracy: 0.752375

Test Set:
Average Loss: 0.6529777946472168
Accuracy: 0.7295
NC1 Within Class Collapse: 5.491887092590332
NC2 Equinorm: Features: 0.14499861001968384, Weights: 0.04881303757429123
NC2 Equiangle: Features: 0.18543692429860434, Weights: 0.03471976021925608
NC3 Self-Duality: 0.22873665392398834
NC4 NCC Mismatch: 0.10750000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.73361587524414
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: 8.743768692016602
Linear Weight Rank: 179
Intra Cos: 0.029253212735056877
Inter Cos: -0.004453428089618683
Norm Quadratic Average: 5.256345272064209
Nearest Class Center Accuracy: 0.604

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.571547746658325
Linear Weight Rank: 4
Intra Cos: 0.10869022458791733
Inter Cos: -0.009037897922098637
Norm Quadratic Average: 3.1054141521453857
Nearest Class Center Accuracy: 0.7045

Output Layer:
Intra Cos: 0.327401340007782
Inter Cos: -0.053550321608781815
Norm Quadratic Average: 3.715627670288086
Nearest Class Center Accuracy: 0.721

