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_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.7925591468811035
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: 7.80166482925415
Linear Weight Rank: 179
Intra Cos: 0.032291755080223083
Inter Cos: -0.005903623066842556
Norm Quadratic Average: 4.690046310424805
Nearest Class Center Accuracy: 0.6155

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4247875213623047
Linear Weight Rank: 4
Intra Cos: 0.14534884691238403
Inter Cos: -0.02379804104566574
Norm Quadratic Average: 2.678478717803955
Nearest Class Center Accuracy: 0.731125

Output Layer:
Intra Cos: 0.3447039723396301
Inter Cos: -0.06307489424943924
Norm Quadratic Average: 3.452723979949951
Nearest Class Center Accuracy: 0.743625

Test Set:
Average Loss: 0.6706479969024658
Accuracy: 0.7275
NC1 Within Class Collapse: 5.4786224365234375
NC2 Equinorm: Features: 0.14574269950389862, Weights: 0.04798686131834984
NC2 Equiangle: Features: 0.18857473134994507, Weights: 0.03197731077671051
NC3 Self-Duality: 0.18481925129890442
NC4 NCC Mismatch: 0.09399999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.7925591468811035
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: 7.80166482925415
Linear Weight Rank: 179
Intra Cos: 0.030262108892202377
Inter Cos: -0.00452818488702178
Norm Quadratic Average: 4.697394371032715
Nearest Class Center Accuracy: 0.6115

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4247875213623047
Linear Weight Rank: 4
Intra Cos: 0.1268349140882492
Inter Cos: -0.009878777898848057
Norm Quadratic Average: 2.662776231765747
Nearest Class Center Accuracy: 0.7005

Output Layer:
Intra Cos: 0.3235582709312439
Inter Cos: -0.04972369223833084
Norm Quadratic Average: 3.4044268131256104
Nearest Class Center Accuracy: 0.719

