Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.775330543518066
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222447380423546
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: 8.784683227539062
Linear Weight Rank: 179
Intra Cos: 0.03072061389684677
Inter Cos: -0.005670750048011541
Norm Quadratic Average: 5.272972106933594
Nearest Class Center Accuracy: 0.61125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6891603469848633
Linear Weight Rank: 4
Intra Cos: 0.1256745606660843
Inter Cos: -0.02192467264831066
Norm Quadratic Average: 3.1654303073883057
Nearest Class Center Accuracy: 0.7395

Output Layer:
Intra Cos: 0.35322514176368713
Inter Cos: -0.07436932623386383
Norm Quadratic Average: 3.947343111038208
Nearest Class Center Accuracy: 0.76025

Test Set:
Average Loss: 0.6403209495544434
Accuracy: 0.735
NC1 Within Class Collapse: 5.396078109741211
NC2 Equinorm: Features: 0.14136964082717896, Weights: 0.04851958155632019
NC2 Equiangle: Features: 0.18321704864501953, Weights: 0.03288718064626058
NC3 Self-Duality: 0.22641205787658691
NC4 NCC Mismatch: 0.11050000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.775330543518066
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724981188774
Norm Quadratic Average: 3.995159864425659
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.784683227539062
Linear Weight Rank: 179
Intra Cos: 0.029209120199084282
Inter Cos: -0.00449697021394968
Norm Quadratic Average: 5.281957149505615
Nearest Class Center Accuracy: 0.6055

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6891603469848633
Linear Weight Rank: 4
Intra Cos: 0.11100661754608154
Inter Cos: -0.009509686380624771
Norm Quadratic Average: 3.1506946086883545
Nearest Class Center Accuracy: 0.709

Output Layer:
Intra Cos: 0.32932278513908386
Inter Cos: -0.055408816784620285
Norm Quadratic Average: 3.892136812210083
Nearest Class Center Accuracy: 0.7285

