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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.216507911682129
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: 8.191137313842773
Linear Weight Rank: 180
Intra Cos: 0.025278350338339806
Inter Cos: -0.004710295703262091
Norm Quadratic Average: 14.081110954284668
Nearest Class Center Accuracy: 0.592

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.839704751968384
Linear Weight Rank: 4
Intra Cos: 0.04024595394730568
Inter Cos: -0.009092598222196102
Norm Quadratic Average: 14.488142013549805
Nearest Class Center Accuracy: 0.815

Output Layer:
Intra Cos: 0.556769609451294
Inter Cos: -0.11490250378847122
Norm Quadratic Average: 7.86876106262207
Nearest Class Center Accuracy: 0.98125

Test Set:
Average Loss: 0.6170765609741211
Accuracy: 0.766
NC1 Within Class Collapse: 5.174015998840332
NC2 Equinorm: Features: 0.13282617926597595, Weights: 0.040779151022434235
NC2 Equiangle: Features: 0.1443970799446106, Weights: 0.03248563160498937
NC3 Self-Duality: 0.5293287634849548
NC4 NCC Mismatch: 0.20999999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.216507911682129
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: 8.191137313842773
Linear Weight Rank: 180
Intra Cos: 0.02315097488462925
Inter Cos: -0.0033745011314749718
Norm Quadratic Average: 14.07027816772461
Nearest Class Center Accuracy: 0.602

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.839704751968384
Linear Weight Rank: 4
Intra Cos: 0.029784657061100006
Inter Cos: -0.004502424970269203
Norm Quadratic Average: 14.475995063781738
Nearest Class Center Accuracy: 0.7165

Output Layer:
Intra Cos: 0.3643936216831207
Inter Cos: -0.05308721214532852
Norm Quadratic Average: 7.786551475524902
Nearest Class Center Accuracy: 0.769

