Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.939980506896973
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: 5.8853583335876465
Linear Weight Rank: 179
Intra Cos: 0.037230439484119415
Inter Cos: -0.003818368539214134
Norm Quadratic Average: 3.556403160095215
Nearest Class Center Accuracy: 0.630125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.116635322570801
Linear Weight Rank: 4
Intra Cos: 0.1984596699476242
Inter Cos: -0.03523669019341469
Norm Quadratic Average: 1.9833801984786987
Nearest Class Center Accuracy: 0.71525

Output Layer:
Intra Cos: 0.3113082945346832
Inter Cos: -0.05692761018872261
Norm Quadratic Average: 2.8597490787506104
Nearest Class Center Accuracy: 0.72125

Test Set:
Average Loss: 0.7192974967956542
Accuracy: 0.707
NC1 Within Class Collapse: 5.531137466430664
NC2 Equinorm: Features: 0.1388835906982422, Weights: 0.04400172457098961
NC2 Equiangle: Features: 0.19476906458536783, Weights: 0.03813259303569794
NC3 Self-Duality: 0.10407464951276779
NC4 NCC Mismatch: 0.08550000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.939980506896973
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: 5.8853583335876465
Linear Weight Rank: 179
Intra Cos: 0.033099960535764694
Inter Cos: -0.0037911483086645603
Norm Quadratic Average: 3.552769422531128
Nearest Class Center Accuracy: 0.6295

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.116635322570801
Linear Weight Rank: 4
Intra Cos: 0.17872285842895508
Inter Cos: -0.015508140437304974
Norm Quadratic Average: 1.9737107753753662
Nearest Class Center Accuracy: 0.694

Output Layer:
Intra Cos: 0.29519593715667725
Inter Cos: -0.03972703590989113
Norm Quadratic Average: 2.8468329906463623
Nearest Class Center Accuracy: 0.6865

