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_314159_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1698492765426636
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.2232694625854492
Linear Weight Rank: 172
Intra Cos: 0.037403203547000885
Inter Cos: -0.004558059852570295
Norm Quadratic Average: 1.4812825918197632
Nearest Class Center Accuracy: 0.62575

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.231886625289917
Linear Weight Rank: 4
Intra Cos: 0.4709322452545166
Inter Cos: -0.13096283376216888
Norm Quadratic Average: 2.30557918548584
Nearest Class Center Accuracy: 0.89225

Output Layer:
Intra Cos: 0.5975655913352966
Inter Cos: -0.15956123173236847
Norm Quadratic Average: 2.705980062484741
Nearest Class Center Accuracy: 0.89225

Test Set:
Average Loss: 0.6073286113739014
Accuracy: 0.759
NC1 Within Class Collapse: 2.9600586891174316
NC2 Equinorm: Features: 0.09325414896011353, Weights: 0.02270316146314144
NC2 Equiangle: Features: 0.09314969182014465, Weights: 0.029359678427378338
NC3 Self-Duality: 0.0378590002655983
NC4 NCC Mismatch: 0.020499999999999963

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1698492765426636
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
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: 1.2232694625854492
Linear Weight Rank: 172
Intra Cos: 0.03330330550670624
Inter Cos: -0.003417014144361019
Norm Quadratic Average: 1.4862065315246582
Nearest Class Center Accuracy: 0.608

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.231886625289917
Linear Weight Rank: 4
Intra Cos: 0.35487282276153564
Inter Cos: -0.05191103741526604
Norm Quadratic Average: 2.2896389961242676
Nearest Class Center Accuracy: 0.7635

Output Layer:
Intra Cos: 0.44619056582450867
Inter Cos: -0.06098421290516853
Norm Quadratic Average: 2.6786422729492188
Nearest Class Center Accuracy: 0.7625

