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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.947731971740723
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: 8.994425773620605
Linear Weight Rank: 179
Intra Cos: 0.16893863677978516
Inter Cos: 0.0048137689009308815
Norm Quadratic Average: 5.617563724517822
Nearest Class Center Accuracy: 0.943125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.0835957527160645
Linear Weight Rank: 4
Intra Cos: 0.595314085483551
Inter Cos: 0.022433847188949585
Norm Quadratic Average: 7.127877235412598
Nearest Class Center Accuracy: 0.9595

Output Layer:
Intra Cos: 0.7770026326179504
Inter Cos: 0.03143817186355591
Norm Quadratic Average: 18.168901443481445
Nearest Class Center Accuracy: 0.965375

Test Set:
Average Loss: 0.0836362795829773
Accuracy: 0.975
NC1 Within Class Collapse: 3.5891549587249756
NC2 Equinorm: Features: 0.038689885288476944, Weights: 0.013814297504723072
NC2 Equiangle: Features: 0.43259302775065106, Weights: 0.3883820374806722
NC3 Self-Duality: 0.059290193021297455
NC4 NCC Mismatch: 0.04249999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.947731971740723
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: 8.994425773620605
Linear Weight Rank: 179
Intra Cos: 0.16673731803894043
Inter Cos: 0.0028724055737257004
Norm Quadratic Average: 5.618340492248535
Nearest Class Center Accuracy: 0.9485

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.0835957527160645
Linear Weight Rank: 4
Intra Cos: 0.5822330713272095
Inter Cos: 0.0133900698274374
Norm Quadratic Average: 7.173620700836182
Nearest Class Center Accuracy: 0.955

Output Layer:
Intra Cos: 0.7568879723548889
Inter Cos: 0.01006124634295702
Norm Quadratic Average: 18.284055709838867
Nearest Class Center Accuracy: 0.957

