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_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.949905872344971
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: 6.0280442237854
Linear Weight Rank: 179
Intra Cos: 0.012067335657775402
Inter Cos: 0.0026003073435276747
Norm Quadratic Average: 10.076109886169434
Nearest Class Center Accuracy: 0.4685

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5434205532073975
Linear Weight Rank: 4
Intra Cos: 0.020032860338687897
Inter Cos: -0.00015615724259987473
Norm Quadratic Average: 10.6282958984375
Nearest Class Center Accuracy: 0.71275

Output Layer:
Intra Cos: 0.5654940009117126
Inter Cos: -0.03624511510133743
Norm Quadratic Average: 3.783942461013794
Nearest Class Center Accuracy: 0.929875

Test Set:
Average Loss: 1.1216390686035156
Accuracy: 0.554
NC1 Within Class Collapse: 12.736417770385742
NC2 Equinorm: Features: 0.020075974985957146, Weights: 0.026176512241363525
NC2 Equiangle: Features: 0.23702740669250488, Weights: 0.03166785091161728
NC3 Self-Duality: 0.7811653017997742
NC4 NCC Mismatch: 0.36250000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.949905872344971
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: 6.0280442237854
Linear Weight Rank: 179
Intra Cos: 0.012883514165878296
Inter Cos: 0.002716163406148553
Norm Quadratic Average: 10.05355453491211
Nearest Class Center Accuracy: 0.476

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5434205532073975
Linear Weight Rank: 4
Intra Cos: 0.010937548242509365
Inter Cos: 0.0014430650044232607
Norm Quadratic Average: 10.659899711608887
Nearest Class Center Accuracy: 0.547

Output Layer:
Intra Cos: 0.16642935574054718
Inter Cos: 0.02223864756524563
Norm Quadratic Average: 3.5999741554260254
Nearest Class Center Accuracy: 0.556

