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_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.130610466003418
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: 5.247501850128174
Linear Weight Rank: 179
Intra Cos: 0.012748928740620613
Inter Cos: 0.004988631699234247
Norm Quadratic Average: 8.74894905090332
Nearest Class Center Accuracy: 0.4695

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4401895999908447
Linear Weight Rank: 4
Intra Cos: 0.02382599376142025
Inter Cos: -0.001524679479189217
Norm Quadratic Average: 9.301883697509766
Nearest Class Center Accuracy: 0.76025

Output Layer:
Intra Cos: 0.5959137678146362
Inter Cos: -0.017123430967330933
Norm Quadratic Average: 3.5648603439331055
Nearest Class Center Accuracy: 0.930125

Test Set:
Average Loss: 1.1073063240051269
Accuracy: 0.5485
NC1 Within Class Collapse: 11.74032211303711
NC2 Equinorm: Features: 0.05783090367913246, Weights: 0.012681585736572742
NC2 Equiangle: Features: 0.23903608322143555, Weights: 0.04268932342529297
NC3 Self-Duality: 0.6501495838165283
NC4 NCC Mismatch: 0.30300000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.130610466003418
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: 5.247501850128174
Linear Weight Rank: 179
Intra Cos: 0.012466412037611008
Inter Cos: 0.004346086643636227
Norm Quadratic Average: 8.705060005187988
Nearest Class Center Accuracy: 0.4735

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4401895999908447
Linear Weight Rank: 4
Intra Cos: 0.012450539506971836
Inter Cos: 0.0009114338317885995
Norm Quadratic Average: 9.32017707824707
Nearest Class Center Accuracy: 0.553

Output Layer:
Intra Cos: 0.17478343844413757
Inter Cos: 0.04077012091875076
Norm Quadratic Average: 3.4386043548583984
Nearest Class Center Accuracy: 0.5465

