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_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.818055629730225
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: 7.881683349609375
Linear Weight Rank: 179
Intra Cos: 0.02724883146584034
Inter Cos: -0.004306758288294077
Norm Quadratic Average: 13.449263572692871
Nearest Class Center Accuracy: 0.59025

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.746622323989868
Linear Weight Rank: 4
Intra Cos: 0.0446305088698864
Inter Cos: -0.008545929566025734
Norm Quadratic Average: 13.87156867980957
Nearest Class Center Accuracy: 0.805125

Output Layer:
Intra Cos: 0.5676088929176331
Inter Cos: -0.09516836702823639
Norm Quadratic Average: 7.519276142120361
Nearest Class Center Accuracy: 0.9785

Test Set:
Average Loss: 0.6233658180236816
Accuracy: 0.7675
NC1 Within Class Collapse: 5.322329044342041
NC2 Equinorm: Features: 0.13944269716739655, Weights: 0.050197165459394455
NC2 Equiangle: Features: 0.14045344789822897, Weights: 0.03339183330535889
NC3 Self-Duality: 0.5727131366729736
NC4 NCC Mismatch: 0.247

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.818055629730225
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: 7.881683349609375
Linear Weight Rank: 179
Intra Cos: 0.026172684505581856
Inter Cos: -0.0037120103370398283
Norm Quadratic Average: 13.503933906555176
Nearest Class Center Accuracy: 0.5815

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.746622323989868
Linear Weight Rank: 4
Intra Cos: 0.03317189961671829
Inter Cos: -0.0034360222052782774
Norm Quadratic Average: 13.910096168518066
Nearest Class Center Accuracy: 0.6885

Output Layer:
Intra Cos: 0.37426626682281494
Inter Cos: -0.044044844806194305
Norm Quadratic Average: 7.369801998138428
Nearest Class Center Accuracy: 0.7585

