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_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.6083855628967285
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: 6.618193626403809
Linear Weight Rank: 178
Intra Cos: 0.03540491312742233
Inter Cos: -0.0063955774530768394
Norm Quadratic Average: 3.9927585124969482
Nearest Class Center Accuracy: 0.622875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.220010995864868
Linear Weight Rank: 4
Intra Cos: 0.17574143409729004
Inter Cos: -0.027682596817612648
Norm Quadratic Average: 2.2092273235321045
Nearest Class Center Accuracy: 0.720375

Output Layer:
Intra Cos: 0.3366057872772217
Inter Cos: -0.052253417670726776
Norm Quadratic Average: 3.0593693256378174
Nearest Class Center Accuracy: 0.727

Test Set:
Average Loss: 0.7018257598876954
Accuracy: 0.713
NC1 Within Class Collapse: 5.52851676940918
NC2 Equinorm: Features: 0.14914420247077942, Weights: 0.04464251920580864
NC2 Equiangle: Features: 0.1952203114827474, Weights: 0.041478633880615234
NC3 Self-Duality: 0.1375575065612793
NC4 NCC Mismatch: 0.09550000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.6083855628967285
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: 6.618193626403809
Linear Weight Rank: 178
Intra Cos: 0.03229577839374542
Inter Cos: -0.004448802676051855
Norm Quadratic Average: 3.997565507888794
Nearest Class Center Accuracy: 0.62

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.220010995864868
Linear Weight Rank: 4
Intra Cos: 0.15444160997867584
Inter Cos: -0.011237605474889278
Norm Quadratic Average: 2.1927316188812256
Nearest Class Center Accuracy: 0.6925

Output Layer:
Intra Cos: 0.3107163906097412
Inter Cos: -0.04264261946082115
Norm Quadratic Average: 3.0198378562927246
Nearest Class Center Accuracy: 0.7005

