Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_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: 5.953519344329834
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: 5.936205863952637
Linear Weight Rank: 179
Intra Cos: 0.030468348413705826
Inter Cos: -0.0040981038473546505
Norm Quadratic Average: 10.090923309326172
Nearest Class Center Accuracy: 0.60175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.440993547439575
Linear Weight Rank: 4
Intra Cos: 0.05611008405685425
Inter Cos: -0.012245713733136654
Norm Quadratic Average: 10.572355270385742
Nearest Class Center Accuracy: 0.888375

Output Layer:
Intra Cos: 0.5970343947410583
Inter Cos: -0.14760060608386993
Norm Quadratic Average: 6.327393054962158
Nearest Class Center Accuracy: 0.9815

Test Set:
Average Loss: 0.58855513381958
Accuracy: 0.768
NC1 Within Class Collapse: 4.312964916229248
NC2 Equinorm: Features: 0.11852576583623886, Weights: 0.03915560245513916
NC2 Equiangle: Features: 0.11722517013549805, Weights: 0.024137606223424275
NC3 Self-Duality: 0.38113027811050415
NC4 NCC Mismatch: 0.14600000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.953519344329834
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: 5.936205863952637
Linear Weight Rank: 179
Intra Cos: 0.027091804891824722
Inter Cos: -0.004066502209752798
Norm Quadratic Average: 10.094240188598633
Nearest Class Center Accuracy: 0.603

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.440993547439575
Linear Weight Rank: 4
Intra Cos: 0.04279111698269844
Inter Cos: -0.005898331757634878
Norm Quadratic Average: 10.583946228027344
Nearest Class Center Accuracy: 0.749

Output Layer:
Intra Cos: 0.3827093541622162
Inter Cos: -0.06752528995275497
Norm Quadratic Average: 6.219266891479492
Nearest Class Center Accuracy: 0.772

