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_979323_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.575453758239746
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.001758486032485962
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: 6.66747522354126
Linear Weight Rank: 179
Intra Cos: 0.21354016661643982
Inter Cos: 0.00528826005756855
Norm Quadratic Average: 4.212446689605713
Nearest Class Center Accuracy: 0.949375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5945987701416016
Linear Weight Rank: 4
Intra Cos: 0.641637921333313
Inter Cos: 0.027403701096773148
Norm Quadratic Average: 5.086791515350342
Nearest Class Center Accuracy: 0.961

Output Layer:
Intra Cos: 0.7824868559837341
Inter Cos: 0.03212837129831314
Norm Quadratic Average: 11.701213836669922
Nearest Class Center Accuracy: 0.96625

Test Set:
Average Loss: 0.11628388786315919
Accuracy: 0.981
NC1 Within Class Collapse: 3.3182406425476074
NC2 Equinorm: Features: 0.03595087304711342, Weights: 0.012712785042822361
NC2 Equiangle: Features: 0.4320845603942871, Weights: 0.3977423111597697
NC3 Self-Duality: 0.041780974715948105
NC4 NCC Mismatch: 0.03949999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.575453758239746
Linear Weight Rank: 16
Intra Cos: 0.08033028244972229
Inter Cos: 0.003312898799777031
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: 6.66747522354126
Linear Weight Rank: 179
Intra Cos: 0.21113359928131104
Inter Cos: 0.0028376244008541107
Norm Quadratic Average: 4.216897964477539
Nearest Class Center Accuracy: 0.9505

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5945987701416016
Linear Weight Rank: 4
Intra Cos: 0.6276639699935913
Inter Cos: 0.01686267927289009
Norm Quadratic Average: 5.120683670043945
Nearest Class Center Accuracy: 0.9575

Output Layer:
Intra Cos: 0.7683711051940918
Inter Cos: 0.011349351145327091
Norm Quadratic Average: 11.771814346313477
Nearest Class Center Accuracy: 0.962

