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_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.811046600341797
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: 8.945955276489258
Linear Weight Rank: 179
Intra Cos: 0.1747189462184906
Inter Cos: 0.010047413408756256
Norm Quadratic Average: 5.529503345489502
Nearest Class Center Accuracy: 0.958875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.070057392120361
Linear Weight Rank: 4
Intra Cos: 0.6154906153678894
Inter Cos: 0.02755681984126568
Norm Quadratic Average: 6.941924095153809
Nearest Class Center Accuracy: 0.97775

Output Layer:
Intra Cos: 0.8006714582443237
Inter Cos: 0.037102967500686646
Norm Quadratic Average: 17.577877044677734
Nearest Class Center Accuracy: 0.97825

Test Set:
Average Loss: 0.08150674438476563
Accuracy: 0.978
NC1 Within Class Collapse: 2.918614387512207
NC2 Equinorm: Features: 0.04454275593161583, Weights: 0.01257429737597704
NC2 Equiangle: Features: 0.43390512466430664, Weights: 0.38640880584716797
NC3 Self-Duality: 0.06270580738782883
NC4 NCC Mismatch: 0.026000000000000023

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.811046600341797
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: 8.945955276489258
Linear Weight Rank: 179
Intra Cos: 0.17198732495307922
Inter Cos: 0.009482292458415031
Norm Quadratic Average: 5.537481307983398
Nearest Class Center Accuracy: 0.953

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.070057392120361
Linear Weight Rank: 4
Intra Cos: 0.6090490818023682
Inter Cos: 0.02463388629257679
Norm Quadratic Average: 7.007658004760742
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7887295484542847
Inter Cos: 0.02917613461613655
Norm Quadratic Average: 17.730043411254883
Nearest Class Center Accuracy: 0.9765

