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_265358_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.550321578979492
Linear Weight Rank: 16
Intra Cos: 0.014583894982933998
Inter Cos: 0.004829855635762215
Norm Quadratic Average: 3.9931397438049316
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.462095260620117
Linear Weight Rank: 180
Intra Cos: 0.013928921893239021
Inter Cos: 0.003755690297111869
Norm Quadratic Average: 5.030394554138184
Nearest Class Center Accuracy: 0.46975

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6379380226135254
Linear Weight Rank: 4
Intra Cos: 0.040077682584524155
Inter Cos: 0.011752803809940815
Norm Quadratic Average: 2.511003017425537
Nearest Class Center Accuracy: 0.53675

Output Layer:
Intra Cos: 0.18058355152606964
Inter Cos: 0.06077678129076958
Norm Quadratic Average: 1.653578281402588
Nearest Class Center Accuracy: 0.554

Test Set:
Average Loss: 1.1007624168395995
Accuracy: 0.5275
NC1 Within Class Collapse: 16.259788513183594
NC2 Equinorm: Features: 0.04309145361185074, Weights: 0.049793656915426254
NC2 Equiangle: Features: 0.37181862195332843, Weights: 0.09488672018051147
NC3 Self-Duality: 0.3847227692604065
NC4 NCC Mismatch: 0.16249999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.550321578979492
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
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: 8.462095260620117
Linear Weight Rank: 180
Intra Cos: 0.014564227312803268
Inter Cos: 0.003969026729464531
Norm Quadratic Average: 5.0215888023376465
Nearest Class Center Accuracy: 0.478

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6379380226135254
Linear Weight Rank: 4
Intra Cos: 0.036869462579488754
Inter Cos: 0.011498134583234787
Norm Quadratic Average: 2.498356819152832
Nearest Class Center Accuracy: 0.527

Output Layer:
Intra Cos: 0.14980684220790863
Inter Cos: 0.05334760248661041
Norm Quadratic Average: 1.6262569427490234
Nearest Class Center Accuracy: 0.521

