Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.267685890197754
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.21921443939209
Linear Weight Rank: 179
Intra Cos: 0.02983582206070423
Inter Cos: -0.004086160100996494
Norm Quadratic Average: 14.009765625
Nearest Class Center Accuracy: 0.598

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9250683784484863
Linear Weight Rank: 4
Intra Cos: 0.04202067106962204
Inter Cos: -0.010108302347362041
Norm Quadratic Average: 14.469066619873047
Nearest Class Center Accuracy: 0.822375

Output Layer:
Intra Cos: 0.5761205554008484
Inter Cos: -0.1286792755126953
Norm Quadratic Average: 7.957849025726318
Nearest Class Center Accuracy: 0.9875

Test Set:
Average Loss: 0.637267988204956
Accuracy: 0.764
NC1 Within Class Collapse: 5.1623334884643555
NC2 Equinorm: Features: 0.10968354344367981, Weights: 0.04076433926820755
NC2 Equiangle: Features: 0.11782575647036235, Weights: 0.0323427269856135
NC3 Self-Duality: 0.5448060035705566
NC4 NCC Mismatch: 0.22699999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.267685890197754
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: 8.21921443939209
Linear Weight Rank: 179
Intra Cos: 0.02671331726014614
Inter Cos: -0.004047031048685312
Norm Quadratic Average: 14.021592140197754
Nearest Class Center Accuracy: 0.6005

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9250683784484863
Linear Weight Rank: 4
Intra Cos: 0.03168001025915146
Inter Cos: -0.006290527060627937
Norm Quadratic Average: 14.4891357421875
Nearest Class Center Accuracy: 0.715

Output Layer:
Intra Cos: 0.36029863357543945
Inter Cos: -0.07223974168300629
Norm Quadratic Average: 7.800529479980469
Nearest Class Center Accuracy: 0.7615

