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_979323_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.154638290405273
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.139273643493652
Linear Weight Rank: 180
Intra Cos: 0.02546650916337967
Inter Cos: -0.004745824262499809
Norm Quadratic Average: 12.249008178710938
Nearest Class Center Accuracy: 0.5925

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6739509105682373
Linear Weight Rank: 4
Intra Cos: 0.04586132988333702
Inter Cos: -0.01046903058886528
Norm Quadratic Average: 12.696247100830078
Nearest Class Center Accuracy: 0.851125

Output Layer:
Intra Cos: 0.5690078735351562
Inter Cos: -0.12053998559713364
Norm Quadratic Average: 7.215208053588867
Nearest Class Center Accuracy: 0.980375

Test Set:
Average Loss: 0.5922411270141602
Accuracy: 0.767
NC1 Within Class Collapse: 4.766512393951416
NC2 Equinorm: Features: 0.1279289424419403, Weights: 0.04049304127693176
NC2 Equiangle: Features: 0.1434540053208669, Weights: 0.02827731768290202
NC3 Self-Duality: 0.4492756426334381
NC4 NCC Mismatch: 0.18300000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.154638290405273
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
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: 7.139273643493652
Linear Weight Rank: 180
Intra Cos: 0.023292390629649162
Inter Cos: -0.003368780482560396
Norm Quadratic Average: 12.239752769470215
Nearest Class Center Accuracy: 0.602

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6739509105682373
Linear Weight Rank: 4
Intra Cos: 0.03357316553592682
Inter Cos: -0.004986647050827742
Norm Quadratic Average: 12.693818092346191
Nearest Class Center Accuracy: 0.737

Output Layer:
Intra Cos: 0.37385231256484985
Inter Cos: -0.0550183542072773
Norm Quadratic Average: 7.144142150878906
Nearest Class Center Accuracy: 0.769

