Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.138235092163086
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.113917350769043
Linear Weight Rank: 180
Intra Cos: 0.025316033512353897
Inter Cos: -0.004726320039480925
Norm Quadratic Average: 13.94654655456543
Nearest Class Center Accuracy: 0.591875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8280794620513916
Linear Weight Rank: 4
Intra Cos: 0.040572162717580795
Inter Cos: -0.009226799942553043
Norm Quadratic Average: 14.356703758239746
Nearest Class Center Accuracy: 0.817625

Output Layer:
Intra Cos: 0.5570157170295715
Inter Cos: -0.11515195667743683
Norm Quadratic Average: 7.814939975738525
Nearest Class Center Accuracy: 0.98075

Test Set:
Average Loss: 0.6166256532669068
Accuracy: 0.768
NC1 Within Class Collapse: 5.151156425476074
NC2 Equinorm: Features: 0.1322920322418213, Weights: 0.04094627872109413
NC2 Equiangle: Features: 0.14328208565711975, Weights: 0.0322518323858579
NC3 Self-Duality: 0.5250663757324219
NC4 NCC Mismatch: 0.20899999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.138235092163086
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.113917350769043
Linear Weight Rank: 180
Intra Cos: 0.02316861040890217
Inter Cos: -0.0033861910924315453
Norm Quadratic Average: 13.935367584228516
Nearest Class Center Accuracy: 0.602

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8280794620513916
Linear Weight Rank: 4
Intra Cos: 0.029978878796100616
Inter Cos: -0.004606781993061304
Norm Quadratic Average: 14.345008850097656
Nearest Class Center Accuracy: 0.717

Output Layer:
Intra Cos: 0.36450639367103577
Inter Cos: -0.05376875400543213
Norm Quadratic Average: 7.733948707580566
Nearest Class Center Accuracy: 0.7655

