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_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0614304542541504
Linear Weight Rank: 16
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: 3.3055901527404785
Linear Weight Rank: 177
Intra Cos: 0.4901587665081024
Inter Cos: 0.009162411093711853
Norm Quadratic Average: 2.1775803565979004
Nearest Class Center Accuracy: 0.981125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.857724666595459
Linear Weight Rank: 4
Intra Cos: 0.7361429333686829
Inter Cos: 0.020988713949918747
Norm Quadratic Average: 2.8499414920806885
Nearest Class Center Accuracy: 0.98475

Output Layer:
Intra Cos: 0.8313042521476746
Inter Cos: 0.01878339797258377
Norm Quadratic Average: 5.394628524780273
Nearest Class Center Accuracy: 0.986125

Test Set:
Average Loss: 0.22834340572357179
Accuracy: 0.9875
NC1 Within Class Collapse: 2.8629302978515625
NC2 Equinorm: Features: 0.035205740481615067, Weights: 0.015480360947549343
NC2 Equiangle: Features: 0.43453391393025714, Weights: 0.4120841423670451
NC3 Self-Duality: 0.012542682699859142
NC4 NCC Mismatch: 0.025499999999999967

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0614304542541504
Linear Weight Rank: 16
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: 3.3055901527404785
Linear Weight Rank: 177
Intra Cos: 0.48329949378967285
Inter Cos: 0.028663037344813347
Norm Quadratic Average: 2.1917917728424072
Nearest Class Center Accuracy: 0.971

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.857724666595459
Linear Weight Rank: 4
Intra Cos: 0.7364203333854675
Inter Cos: 0.046625565737485886
Norm Quadratic Average: 2.8743627071380615
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.8301275372505188
Inter Cos: 0.046274539083242416
Norm Quadratic Average: 5.432327747344971
Nearest Class Center Accuracy: 0.9815

