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_846264_weight_decay_0.0007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.716026306152344
Linear Weight Rank: 16
Intra Cos: 0.07988917082548141
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: 8.81157398223877
Linear Weight Rank: 179
Intra Cos: 0.17398729920387268
Inter Cos: 0.006060928571969271
Norm Quadratic Average: 5.449756145477295
Nearest Class Center Accuracy: 0.95925

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.043956756591797
Linear Weight Rank: 4
Intra Cos: 0.612791895866394
Inter Cos: 0.027709579095244408
Norm Quadratic Average: 6.850086688995361
Nearest Class Center Accuracy: 0.973125

Output Layer:
Intra Cos: 0.7903931140899658
Inter Cos: 0.04030391201376915
Norm Quadratic Average: 17.36566162109375
Nearest Class Center Accuracy: 0.9735

Test Set:
Average Loss: 0.08720911860466003
Accuracy: 0.979
NC1 Within Class Collapse: 2.9682068824768066
NC2 Equinorm: Features: 0.03854566439986229, Weights: 0.016617024317383766
NC2 Equiangle: Features: 0.4344828923543294, Weights: 0.39460571606953937
NC3 Self-Duality: 0.05497603118419647
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.716026306152344
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
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: 8.81157398223877
Linear Weight Rank: 179
Intra Cos: 0.17127417027950287
Inter Cos: 0.006769743748009205
Norm Quadratic Average: 5.457736015319824
Nearest Class Center Accuracy: 0.953

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.043956756591797
Linear Weight Rank: 4
Intra Cos: 0.6052172183990479
Inter Cos: 0.0500633642077446
Norm Quadratic Average: 6.917998313903809
Nearest Class Center Accuracy: 0.964

Output Layer:
Intra Cos: 0.780587911605835
Inter Cos: 0.06724238395690918
Norm Quadratic Average: 17.537334442138672
Nearest Class Center Accuracy: 0.967

