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_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.9531261920928955
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: 3.0209426879882812
Linear Weight Rank: 177
Intra Cos: 0.07168080657720566
Inter Cos: -0.011102077551186085
Norm Quadratic Average: 1.9172492027282715
Nearest Class Center Accuracy: 0.6265

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3738505840301514
Linear Weight Rank: 4
Intra Cos: 0.21774525940418243
Inter Cos: -0.019044090062379837
Norm Quadratic Average: 1.3185501098632812
Nearest Class Center Accuracy: 0.637625

Output Layer:
Intra Cos: 0.234253391623497
Inter Cos: -0.007454098667949438
Norm Quadratic Average: 1.771328091621399
Nearest Class Center Accuracy: 0.63275

Test Set:
Average Loss: 0.9035324401855469
Accuracy: 0.6345
NC1 Within Class Collapse: 7.315401077270508
NC2 Equinorm: Features: 0.16954763233661652, Weights: 0.02618037909269333
NC2 Equiangle: Features: 0.23692754904429117, Weights: 0.10596464077631633
NC3 Self-Duality: 0.050410687923431396
NC4 NCC Mismatch: 0.08099999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.9531261920928955
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: 3.0209426879882812
Linear Weight Rank: 177
Intra Cos: 0.06517268717288971
Inter Cos: -0.004904553294181824
Norm Quadratic Average: 1.91367506980896
Nearest Class Center Accuracy: 0.613

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3738505840301514
Linear Weight Rank: 4
Intra Cos: 0.18889299035072327
Inter Cos: 0.0014654817059636116
Norm Quadratic Average: 1.3111798763275146
Nearest Class Center Accuracy: 0.62

Output Layer:
Intra Cos: 0.20583981275558472
Inter Cos: 0.010183794423937798
Norm Quadratic Average: 1.7599433660507202
Nearest Class Center Accuracy: 0.6245

