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_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.003378868103027
Linear Weight Rank: 16
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: 4.2133049964904785
Linear Weight Rank: 178
Intra Cos: 0.36384451389312744
Inter Cos: 0.004223233088850975
Norm Quadratic Average: 2.715898275375366
Nearest Class Center Accuracy: 0.978125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.078432559967041
Linear Weight Rank: 4
Intra Cos: 0.7145669460296631
Inter Cos: 0.031040556728839874
Norm Quadratic Average: 3.4007568359375
Nearest Class Center Accuracy: 0.980875

Output Layer:
Intra Cos: 0.814145028591156
Inter Cos: 0.034786246716976166
Norm Quadratic Average: 6.89831018447876
Nearest Class Center Accuracy: 0.9805

Test Set:
Average Loss: 0.17901221656799315
Accuracy: 0.9875
NC1 Within Class Collapse: 2.5835776329040527
NC2 Equinorm: Features: 0.0399806834757328, Weights: 0.017321476712822914
NC2 Equiangle: Features: 0.4348564147949219, Weights: 0.4149649937947591
NC3 Self-Duality: 0.018844690173864365
NC4 NCC Mismatch: 0.026499999999999968

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.003378868103027
Linear Weight Rank: 16
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: 4.2133049964904785
Linear Weight Rank: 178
Intra Cos: 0.35970109701156616
Inter Cos: 0.01746964082121849
Norm Quadratic Average: 2.729482650756836
Nearest Class Center Accuracy: 0.972

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.078432559967041
Linear Weight Rank: 4
Intra Cos: 0.7080274820327759
Inter Cos: 0.0545213520526886
Norm Quadratic Average: 3.431515693664551
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.8081248998641968
Inter Cos: 0.061148710548877716
Norm Quadratic Average: 6.950929164886475
Nearest Class Center Accuracy: 0.977

