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_979323_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.138193130493164
Linear Weight Rank: 16
Intra Cos: 0.014583897776901722
Inter Cos: 0.004829857032746077
Norm Quadratic Average: 3.9931399822235107
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.186408996582031
Linear Weight Rank: 179
Intra Cos: 0.012540592812001705
Inter Cos: 0.004845934920012951
Norm Quadratic Average: 13.963044166564941
Nearest Class Center Accuracy: 0.4675

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8609657287597656
Linear Weight Rank: 4
Intra Cos: 0.016057927161455154
Inter Cos: 0.0004204638535156846
Norm Quadratic Average: 14.368962287902832
Nearest Class Center Accuracy: 0.6185

Output Layer:
Intra Cos: 0.5572118163108826
Inter Cos: -0.01950255036354065
Norm Quadratic Average: 4.287328243255615
Nearest Class Center Accuracy: 0.932125

Test Set:
Average Loss: 1.1980173759460448
Accuracy: 0.549
NC1 Within Class Collapse: 14.927288055419922
NC2 Equinorm: Features: 0.061213523149490356, Weights: 0.008719200268387794
NC2 Equiangle: Features: 0.2300144632657369, Weights: 0.046451469262441
NC3 Self-Duality: 1.0262945890426636
NC4 NCC Mismatch: 0.40149999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.138193130493164
Linear Weight Rank: 16
Intra Cos: 0.014108890667557716
Inter Cos: 0.005012288689613342
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: 8.186408996582031
Linear Weight Rank: 179
Intra Cos: 0.01224671583622694
Inter Cos: 0.0041531845927238464
Norm Quadratic Average: 13.900164604187012
Nearest Class Center Accuracy: 0.4685

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8609657287597656
Linear Weight Rank: 4
Intra Cos: 0.010445976629853249
Inter Cos: 0.0011013811454176903
Norm Quadratic Average: 14.335604667663574
Nearest Class Center Accuracy: 0.528

Output Layer:
Intra Cos: 0.16035373508930206
Inter Cos: 0.03367306664586067
Norm Quadratic Average: 4.162236213684082
Nearest Class Center Accuracy: 0.54

