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_846264_weight_decay_0.07.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.0033719539642334
Linear Weight Rank: 15
Intra Cos: 0.07988917082548141
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.289777994155884
Linear Weight Rank: 168
Intra Cos: 0.7170044779777527
Inter Cos: 0.020549973472952843
Norm Quadratic Average: 1.5236566066741943
Nearest Class Center Accuracy: 0.980125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3540916442871094
Linear Weight Rank: 3
Intra Cos: 0.7656899094581604
Inter Cos: 0.023808136582374573
Norm Quadratic Average: 1.9286890029907227
Nearest Class Center Accuracy: 0.982

Output Layer:
Intra Cos: 0.8374065160751343
Inter Cos: 0.02390115149319172
Norm Quadratic Average: 3.0834052562713623
Nearest Class Center Accuracy: 0.982875

Test Set:
Average Loss: 0.39798187828063963
Accuracy: 0.9835
NC1 Within Class Collapse: 6.976418495178223
NC2 Equinorm: Features: 0.041512005031108856, Weights: 0.017085794359445572
NC2 Equiangle: Features: 0.4410657485326131, Weights: 0.434420108795166
NC3 Self-Duality: 0.004400298465043306
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.0033719539642334
Linear Weight Rank: 15
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: 2.289777994155884
Linear Weight Rank: 168
Intra Cos: 0.725289523601532
Inter Cos: 0.04273757338523865
Norm Quadratic Average: 1.5377558469772339
Nearest Class Center Accuracy: 0.9735

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3540916442871094
Linear Weight Rank: 3
Intra Cos: 0.7625047564506531
Inter Cos: 0.04964335635304451
Norm Quadratic Average: 1.942760944366455
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.8335365653038025
Inter Cos: 0.0510881207883358
Norm Quadratic Average: 3.1008880138397217
Nearest Class Center Accuracy: 0.981

