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_338327_weight_decay_0.0007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.719377517700195
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.793916702270508
Linear Weight Rank: 180
Intra Cos: 0.1790233701467514
Inter Cos: 0.002613792195916176
Norm Quadratic Average: 5.3987884521484375
Nearest Class Center Accuracy: 0.957125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.063539505004883
Linear Weight Rank: 4
Intra Cos: 0.6373150944709778
Inter Cos: 0.02432042919099331
Norm Quadratic Average: 6.780071258544922
Nearest Class Center Accuracy: 0.982125

Output Layer:
Intra Cos: 0.8167202472686768
Inter Cos: 0.03553372621536255
Norm Quadratic Average: 17.226213455200195
Nearest Class Center Accuracy: 0.9825

Test Set:
Average Loss: 0.0869373254776001
Accuracy: 0.9835
NC1 Within Class Collapse: 2.7798914909362793
NC2 Equinorm: Features: 0.04469623789191246, Weights: 0.017144721001386642
NC2 Equiangle: Features: 0.4344019889831543, Weights: 0.3885617256164551
NC3 Self-Duality: 0.059532083570957184
NC4 NCC Mismatch: 0.029000000000000026

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.719377517700195
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 8.793916702270508
Linear Weight Rank: 180
Intra Cos: 0.1763603389263153
Inter Cos: 0.007309875451028347
Norm Quadratic Average: 5.404707431793213
Nearest Class Center Accuracy: 0.953

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.063539505004883
Linear Weight Rank: 4
Intra Cos: 0.6311612725257874
Inter Cos: 0.04823846369981766
Norm Quadratic Average: 6.85009241104126
Nearest Class Center Accuracy: 0.9725

Output Layer:
Intra Cos: 0.8051033616065979
Inter Cos: 0.06447362154722214
Norm Quadratic Average: 17.399169921875
Nearest Class Center Accuracy: 0.975

