Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.092198371887207
Linear Weight Rank: 16
Intra Cos: 0.014583898708224297
Inter Cos: 0.004829856567084789
Norm Quadratic Average: 3.993140459060669
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.252946853637695
Linear Weight Rank: 179
Intra Cos: 0.012535800226032734
Inter Cos: 0.004519414156675339
Norm Quadratic Average: 12.27675724029541
Nearest Class Center Accuracy: 0.46525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.744786024093628
Linear Weight Rank: 4
Intra Cos: 0.016272246837615967
Inter Cos: -0.0008842992829158902
Norm Quadratic Average: 12.758538246154785
Nearest Class Center Accuracy: 0.661875

Output Layer:
Intra Cos: 0.5600101947784424
Inter Cos: -0.02997004985809326
Norm Quadratic Average: 4.107504844665527
Nearest Class Center Accuracy: 0.934875

Test Set:
Average Loss: 1.1842888679504395
Accuracy: 0.5385
NC1 Within Class Collapse: 14.810023307800293
NC2 Equinorm: Features: 0.054818253964185715, Weights: 0.02783551625907421
NC2 Equiangle: Features: 0.20441007614135742, Weights: 0.0349188894033432
NC3 Self-Duality: 0.8950548768043518
NC4 NCC Mismatch: 0.40049999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.092198371887207
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012289620935917
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.252946853637695
Linear Weight Rank: 179
Intra Cos: 0.013650080189108849
Inter Cos: 0.004449713509529829
Norm Quadratic Average: 12.227157592773438
Nearest Class Center Accuracy: 0.4635

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.744786024093628
Linear Weight Rank: 4
Intra Cos: 0.009082596749067307
Inter Cos: 0.00034451682586222887
Norm Quadratic Average: 12.786941528320312
Nearest Class Center Accuracy: 0.528

Output Layer:
Intra Cos: 0.15861453115940094
Inter Cos: 0.028193704783916473
Norm Quadratic Average: 3.9404070377349854
Nearest Class Center Accuracy: 0.5405

