Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_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: 8.418068885803223
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: 8.351067543029785
Linear Weight Rank: 179
Intra Cos: 0.014475365169346333
Inter Cos: 0.006513509899377823
Norm Quadratic Average: 5.052806377410889
Nearest Class Center Accuracy: 0.467875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.577566146850586
Linear Weight Rank: 4
Intra Cos: 0.040963541716337204
Inter Cos: 0.017930645495653152
Norm Quadratic Average: 2.4899871349334717
Nearest Class Center Accuracy: 0.526

Output Layer:
Intra Cos: 0.17868562042713165
Inter Cos: 0.08118481934070587
Norm Quadratic Average: 1.5940371751785278
Nearest Class Center Accuracy: 0.546875

Test Set:
Average Loss: 1.1129544601440429
Accuracy: 0.5205
NC1 Within Class Collapse: 16.918933868408203
NC2 Equinorm: Features: 0.1092609241604805, Weights: 0.02459132671356201
NC2 Equiangle: Features: 0.3832501967748006, Weights: 0.10048728187878926
NC3 Self-Duality: 0.4047424793243408
NC4 NCC Mismatch: 0.15800000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.418068885803223
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: 8.351067543029785
Linear Weight Rank: 179
Intra Cos: 0.013824607245624065
Inter Cos: 0.006144894286990166
Norm Quadratic Average: 5.027331829071045
Nearest Class Center Accuracy: 0.469

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.577566146850586
Linear Weight Rank: 4
Intra Cos: 0.035399239510297775
Inter Cos: 0.018204789608716965
Norm Quadratic Average: 2.470991373062134
Nearest Class Center Accuracy: 0.5045

Output Layer:
Intra Cos: 0.148916557431221
Inter Cos: 0.07981995493173599
Norm Quadratic Average: 1.5785551071166992
Nearest Class Center Accuracy: 0.512

