Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1680694818496704
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.2173420190811157
Linear Weight Rank: 170
Intra Cos: 0.031977541744709015
Inter Cos: -0.002232880797237158
Norm Quadratic Average: 1.4821763038635254
Nearest Class Center Accuracy: 0.63125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.2387521266937256
Linear Weight Rank: 4
Intra Cos: 0.493203729391098
Inter Cos: -0.14604251086711884
Norm Quadratic Average: 2.2964890003204346
Nearest Class Center Accuracy: 0.89925

Output Layer:
Intra Cos: 0.6178268194198608
Inter Cos: -0.15923044085502625
Norm Quadratic Average: 2.713700294494629
Nearest Class Center Accuracy: 0.89975

Test Set:
Average Loss: 0.6078432693481445
Accuracy: 0.758
NC1 Within Class Collapse: 2.99676775932312
NC2 Equinorm: Features: 0.09200271219015121, Weights: 0.02106747031211853
NC2 Equiangle: Features: 0.0962964693705241, Weights: 0.03226669132709503
NC3 Self-Duality: 0.036317192018032074
NC4 NCC Mismatch: 0.028000000000000025

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1680694818496704
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.2173420190811157
Linear Weight Rank: 170
Intra Cos: 0.026603877544403076
Inter Cos: -0.002392780501395464
Norm Quadratic Average: 1.4828282594680786
Nearest Class Center Accuracy: 0.618

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.2387521266937256
Linear Weight Rank: 4
Intra Cos: 0.36356163024902344
Inter Cos: -0.054919783025979996
Norm Quadratic Average: 2.286712169647217
Nearest Class Center Accuracy: 0.761

Output Layer:
Intra Cos: 0.4502968490123749
Inter Cos: -0.06307266652584076
Norm Quadratic Average: 2.692532777786255
Nearest Class Center Accuracy: 0.7595

