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_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.600386619567871
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: 8.676260948181152
Linear Weight Rank: 180
Intra Cos: 0.18073150515556335
Inter Cos: 0.0026499684900045395
Norm Quadratic Average: 5.32944917678833
Nearest Class Center Accuracy: 0.957875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.038070201873779
Linear Weight Rank: 4
Intra Cos: 0.6399182081222534
Inter Cos: 0.02444232814013958
Norm Quadratic Average: 6.671267986297607
Nearest Class Center Accuracy: 0.982125

Output Layer:
Intra Cos: 0.8169828057289124
Inter Cos: 0.03545517474412918
Norm Quadratic Average: 16.866798400878906
Nearest Class Center Accuracy: 0.9825

Test Set:
Average Loss: 0.08829781603813171
Accuracy: 0.9835
NC1 Within Class Collapse: 2.7708077430725098
NC2 Equinorm: Features: 0.04463071748614311, Weights: 0.017141317948698997
NC2 Equiangle: Features: 0.43436622619628906, Weights: 0.3890620867411296
NC3 Self-Duality: 0.05861543491482735
NC4 NCC Mismatch: 0.029000000000000026

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.600386619567871
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: 8.676260948181152
Linear Weight Rank: 180
Intra Cos: 0.17803534865379333
Inter Cos: 0.007362609729170799
Norm Quadratic Average: 5.335477828979492
Nearest Class Center Accuracy: 0.9535

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.038070201873779
Linear Weight Rank: 4
Intra Cos: 0.6335028409957886
Inter Cos: 0.04836373031139374
Norm Quadratic Average: 6.740170001983643
Nearest Class Center Accuracy: 0.9725

Output Layer:
Intra Cos: 0.8053716421127319
Inter Cos: 0.06436530500650406
Norm Quadratic Average: 17.035436630249023
Nearest Class Center Accuracy: 0.975

