Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_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: 1.8754585981369019
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: 2.0240159034729004
Linear Weight Rank: 175
Intra Cos: 0.12198111414909363
Inter Cos: -0.009257839061319828
Norm Quadratic Average: 1.3350915908813477
Nearest Class Center Accuracy: 0.5945

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9480624198913574
Linear Weight Rank: 4
Intra Cos: 0.18091383576393127
Inter Cos: 0.00462260190397501
Norm Quadratic Average: 1.086325764656067
Nearest Class Center Accuracy: 0.59075

Output Layer:
Intra Cos: 0.181056410074234
Inter Cos: 0.018236765637993813
Norm Quadratic Average: 1.2502878904342651
Nearest Class Center Accuracy: 0.579125

Test Set:
Average Loss: 1.0144812698364258
Accuracy: 0.6075
NC1 Within Class Collapse: 8.700813293457031
NC2 Equinorm: Features: 0.19483910501003265, Weights: 0.05835871398448944
NC2 Equiangle: Features: 0.2847527265548706, Weights: 0.15425231059392294
NC3 Self-Duality: 0.04823652654886246
NC4 NCC Mismatch: 0.09899999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.8754585981369019
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: 2.0240159034729004
Linear Weight Rank: 175
Intra Cos: 0.11059059947729111
Inter Cos: -0.0018511014059185982
Norm Quadratic Average: 1.3307182788848877
Nearest Class Center Accuracy: 0.5875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9480624198913574
Linear Weight Rank: 4
Intra Cos: 0.16239142417907715
Inter Cos: 0.019887015223503113
Norm Quadratic Average: 1.0805914402008057
Nearest Class Center Accuracy: 0.5905

Output Layer:
Intra Cos: 0.16774514317512512
Inter Cos: 0.035058338195085526
Norm Quadratic Average: 1.2425918579101562
Nearest Class Center Accuracy: 0.5785

