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_265358_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.163031101226807
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: 5.26313591003418
Linear Weight Rank: 179
Intra Cos: 0.012102543376386166
Inter Cos: 0.002592981792986393
Norm Quadratic Average: 8.719588279724121
Nearest Class Center Accuracy: 0.46925

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.422591209411621
Linear Weight Rank: 4
Intra Cos: 0.023779070004820824
Inter Cos: -0.0009315236238762736
Norm Quadratic Average: 9.307679176330566
Nearest Class Center Accuracy: 0.756875

Output Layer:
Intra Cos: 0.579314649105072
Inter Cos: -0.037928663194179535
Norm Quadratic Average: 3.572448968887329
Nearest Class Center Accuracy: 0.933625

Test Set:
Average Loss: 1.1055218162536622
Accuracy: 0.551
NC1 Within Class Collapse: 11.602951049804688
NC2 Equinorm: Features: 0.02974614128470421, Weights: 0.027185196056962013
NC2 Equiangle: Features: 0.22390149037043253, Weights: 0.03076651692390442
NC3 Self-Duality: 0.6679993271827698
NC4 NCC Mismatch: 0.32499999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.163031101226807
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: 5.26313591003418
Linear Weight Rank: 179
Intra Cos: 0.012899951077997684
Inter Cos: 0.0026711695827543736
Norm Quadratic Average: 8.698060989379883
Nearest Class Center Accuracy: 0.476

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.422591209411621
Linear Weight Rank: 4
Intra Cos: 0.01161558274179697
Inter Cos: 0.001151164178736508
Norm Quadratic Average: 9.35523509979248
Nearest Class Center Accuracy: 0.5595

Output Layer:
Intra Cos: 0.1740131825208664
Inter Cos: 0.01990835927426815
Norm Quadratic Average: 3.401974678039551
Nearest Class Center Accuracy: 0.5575

