Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.472846031188965
Linear Weight Rank: 16
Intra Cos: 0.014583894982933998
Inter Cos: 0.004829855635762215
Norm Quadratic Average: 3.9931397438049316
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.385502815246582
Linear Weight Rank: 180
Intra Cos: 0.013963672332465649
Inter Cos: 0.003772055497393012
Norm Quadratic Average: 4.985189437866211
Nearest Class Center Accuracy: 0.470625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6266117095947266
Linear Weight Rank: 4
Intra Cos: 0.040711067616939545
Inter Cos: 0.012030272744596004
Norm Quadratic Average: 2.475231647491455
Nearest Class Center Accuracy: 0.53725

Output Layer:
Intra Cos: 0.1799604743719101
Inter Cos: 0.06126184016466141
Norm Quadratic Average: 1.6443179845809937
Nearest Class Center Accuracy: 0.55325

Test Set:
Average Loss: 1.1016838760375978
Accuracy: 0.527
NC1 Within Class Collapse: 16.269563674926758
NC2 Equinorm: Features: 0.04348403215408325, Weights: 0.049799978733062744
NC2 Equiangle: Features: 0.37353992462158203, Weights: 0.09515748421351115
NC3 Self-Duality: 0.3781937062740326
NC4 NCC Mismatch: 0.15849999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.472846031188965
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012288689613342
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.385502815246582
Linear Weight Rank: 180
Intra Cos: 0.014597821980714798
Inter Cos: 0.003986672963947058
Norm Quadratic Average: 4.976415157318115
Nearest Class Center Accuracy: 0.478

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6266117095947266
Linear Weight Rank: 4
Intra Cos: 0.03749097138643265
Inter Cos: 0.011767663061618805
Norm Quadratic Average: 2.4625589847564697
Nearest Class Center Accuracy: 0.5265

Output Layer:
Intra Cos: 0.14963603019714355
Inter Cos: 0.053939349949359894
Norm Quadratic Average: 1.617273211479187
Nearest Class Center Accuracy: 0.5195

