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_265358_weight_decay_0.07.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.99554443359375
Linear Weight Rank: 15
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
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: 2.2900450229644775
Linear Weight Rank: 168
Intra Cos: 0.7199733257293701
Inter Cos: 0.020498260855674744
Norm Quadratic Average: 1.5227152109146118
Nearest Class Center Accuracy: 0.98125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.354081630706787
Linear Weight Rank: 3
Intra Cos: 0.7699538469314575
Inter Cos: 0.02256121300160885
Norm Quadratic Average: 1.9233150482177734
Nearest Class Center Accuracy: 0.98425

Output Layer:
Intra Cos: 0.8354966640472412
Inter Cos: 0.02208455465734005
Norm Quadratic Average: 3.070566177368164
Nearest Class Center Accuracy: 0.984875

Test Set:
Average Loss: 0.40139332962036134
Accuracy: 0.9785
NC1 Within Class Collapse: 6.355411052703857
NC2 Equinorm: Features: 0.03877712041139603, Weights: 0.015328307636082172
NC2 Equiangle: Features: 0.4403843879699707, Weights: 0.4314127763112386
NC3 Self-Duality: 0.004725855775177479
NC4 NCC Mismatch: 0.03400000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.99554443359375
Linear Weight Rank: 15
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
Norm Quadratic Average: 3.9883358478546143
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.2900450229644775
Linear Weight Rank: 168
Intra Cos: 0.7270852327346802
Inter Cos: 0.04551320523023605
Norm Quadratic Average: 1.536576271057129
Nearest Class Center Accuracy: 0.975

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.354081630706787
Linear Weight Rank: 3
Intra Cos: 0.7664867043495178
Inter Cos: 0.04768253490328789
Norm Quadratic Average: 1.937872052192688
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.8395283222198486
Inter Cos: 0.048234518617391586
Norm Quadratic Average: 3.0894830226898193
Nearest Class Center Accuracy: 0.979

