Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.730287551879883
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584841698408127
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.865388870239258
Linear Weight Rank: 179
Intra Cos: 0.17579706013202667
Inter Cos: 0.010078232735395432
Norm Quadratic Average: 5.481477737426758
Nearest Class Center Accuracy: 0.958875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.052577495574951
Linear Weight Rank: 4
Intra Cos: 0.6170926094055176
Inter Cos: 0.02766541764140129
Norm Quadratic Average: 6.8650383949279785
Nearest Class Center Accuracy: 0.97775

Output Layer:
Intra Cos: 0.8008823990821838
Inter Cos: 0.03708814084529877
Norm Quadratic Average: 17.324865341186523
Nearest Class Center Accuracy: 0.97825

Test Set:
Average Loss: 0.08234587359428405
Accuracy: 0.978
NC1 Within Class Collapse: 2.9128241539001465
NC2 Equinorm: Features: 0.04447457566857338, Weights: 0.012611412443220615
NC2 Equiangle: Features: 0.43389058113098145, Weights: 0.38673969109853107
NC3 Self-Duality: 0.06205558404326439
NC4 NCC Mismatch: 0.026000000000000023

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.730287551879883
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.865388870239258
Linear Weight Rank: 179
Intra Cos: 0.17305225133895874
Inter Cos: 0.00949428416788578
Norm Quadratic Average: 5.489526271820068
Nearest Class Center Accuracy: 0.953

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.052577495574951
Linear Weight Rank: 4
Intra Cos: 0.6106464862823486
Inter Cos: 0.024781426414847374
Norm Quadratic Average: 6.930127143859863
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7889707088470459
Inter Cos: 0.02914106845855713
Norm Quadratic Average: 17.474632263183594
Nearest Class Center Accuracy: 0.9765

