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_314159_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.808403015136719
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.818687438964844
Linear Weight Rank: 179
Intra Cos: 0.030564410611987114
Inter Cos: -0.005630257539451122
Norm Quadratic Average: 5.291474342346191
Nearest Class Center Accuracy: 0.6085

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.582681179046631
Linear Weight Rank: 4
Intra Cos: 0.12288327515125275
Inter Cos: -0.02026405744254589
Norm Quadratic Average: 3.1579196453094482
Nearest Class Center Accuracy: 0.733

Output Layer:
Intra Cos: 0.3492608964443207
Inter Cos: -0.06969452649354935
Norm Quadratic Average: 3.7959303855895996
Nearest Class Center Accuracy: 0.75275

Test Set:
Average Loss: 0.6517919273376465
Accuracy: 0.7295
NC1 Within Class Collapse: 5.494595050811768
NC2 Equinorm: Features: 0.1449330598115921, Weights: 0.04877999797463417
NC2 Equiangle: Features: 0.18514792124430338, Weights: 0.035167391101519264
NC3 Self-Duality: 0.23224686086177826
NC4 NCC Mismatch: 0.10899999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.808403015136719
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
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: 8.818687438964844
Linear Weight Rank: 179
Intra Cos: 0.029186489060521126
Inter Cos: -0.004443245939910412
Norm Quadratic Average: 5.300896167755127
Nearest Class Center Accuracy: 0.603

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.582681179046631
Linear Weight Rank: 4
Intra Cos: 0.1074172705411911
Inter Cos: -0.00897984392940998
Norm Quadratic Average: 3.1430752277374268
Nearest Class Center Accuracy: 0.703

Output Layer:
Intra Cos: 0.32748958468437195
Inter Cos: -0.05380183085799217
Norm Quadratic Average: 3.7408812046051025
Nearest Class Center Accuracy: 0.7215

