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_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.913933277130127
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: 5.911880016326904
Linear Weight Rank: 180
Intra Cos: 0.025798937305808067
Inter Cos: -0.004704724065959454
Norm Quadratic Average: 10.103137969970703
Nearest Class Center Accuracy: 0.5955

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.468421459197998
Linear Weight Rank: 4
Intra Cos: 0.05594540014863014
Inter Cos: -0.013330789282917976
Norm Quadratic Average: 10.606698036193848
Nearest Class Center Accuracy: 0.894125

Output Layer:
Intra Cos: 0.5896134376525879
Inter Cos: -0.12949959933757782
Norm Quadratic Average: 6.439844608306885
Nearest Class Center Accuracy: 0.9815

Test Set:
Average Loss: 0.5717664804458619
Accuracy: 0.7675
NC1 Within Class Collapse: 4.269681930541992
NC2 Equinorm: Features: 0.12159959226846695, Weights: 0.03856004402041435
NC2 Equiangle: Features: 0.1431060234705607, Weights: 0.023631577690442402
NC3 Self-Duality: 0.3534233868122101
NC4 NCC Mismatch: 0.14700000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.913933277130127
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: 5.911880016326904
Linear Weight Rank: 180
Intra Cos: 0.0235233623534441
Inter Cos: -0.0031923193018883467
Norm Quadratic Average: 10.095876693725586
Nearest Class Center Accuracy: 0.6045

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.468421459197998
Linear Weight Rank: 4
Intra Cos: 0.040857475250959396
Inter Cos: -0.0059622302651405334
Norm Quadratic Average: 10.613751411437988
Nearest Class Center Accuracy: 0.7575

Output Layer:
Intra Cos: 0.383791446685791
Inter Cos: -0.054298967123031616
Norm Quadratic Average: 6.372321605682373
Nearest Class Center Accuracy: 0.7665

