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_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.079403877258301
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: 2.207768678665161
Linear Weight Rank: 178
Intra Cos: 0.029922965914011
Inter Cos: -0.005400972906500101
Norm Quadratic Average: 3.3766984939575195
Nearest Class Center Accuracy: 0.612125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.738010883331299
Linear Weight Rank: 4
Intra Cos: 0.19594520330429077
Inter Cos: -0.05384998023509979
Norm Quadratic Average: 4.151708602905273
Nearest Class Center Accuracy: 0.942

Output Layer:
Intra Cos: 0.6863760352134705
Inter Cos: -0.17165115475654602
Norm Quadratic Average: 3.676100730895996
Nearest Class Center Accuracy: 0.964375

Test Set:
Average Loss: 0.5708288269042969
Accuracy: 0.7625
NC1 Within Class Collapse: 3.115551233291626
NC2 Equinorm: Features: 0.09226217120885849, Weights: 0.031674012541770935
NC2 Equiangle: Features: 0.11818474531173706, Weights: 0.017314439018567402
NC3 Self-Duality: 0.15708160400390625
NC4 NCC Mismatch: 0.05300000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.079403877258301
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: 2.207768678665161
Linear Weight Rank: 178
Intra Cos: 0.02673901431262493
Inter Cos: -0.003032647306099534
Norm Quadratic Average: 3.372337579727173
Nearest Class Center Accuracy: 0.6115

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.738010883331299
Linear Weight Rank: 4
Intra Cos: 0.13765351474285126
Inter Cos: -0.019376391544938087
Norm Quadratic Average: 4.156952381134033
Nearest Class Center Accuracy: 0.762

Output Layer:
Intra Cos: 0.4526083171367645
Inter Cos: -0.06645337492227554
Norm Quadratic Average: 3.6377482414245605
Nearest Class Center Accuracy: 0.764

