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_265358_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0007591247558594
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 3.0414226055145264
Linear Weight Rank: 178
Intra Cos: 0.06783605366945267
Inter Cos: -0.00969991460442543
Norm Quadratic Average: 1.9259284734725952
Nearest Class Center Accuracy: 0.62525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.4075510501861572
Linear Weight Rank: 4
Intra Cos: 0.23025858402252197
Inter Cos: -0.024824241176247597
Norm Quadratic Average: 1.3098896741867065
Nearest Class Center Accuracy: 0.6415

Output Layer:
Intra Cos: 0.252002090215683
Inter Cos: -0.01548628881573677
Norm Quadratic Average: 1.7752456665039062
Nearest Class Center Accuracy: 0.636375

Test Set:
Average Loss: 0.8948239479064941
Accuracy: 0.641
NC1 Within Class Collapse: 6.839838981628418
NC2 Equinorm: Features: 0.16165192425251007, Weights: 0.021962491795420647
NC2 Equiangle: Features: 0.22582236925760904, Weights: 0.08203928669293721
NC3 Self-Duality: 0.05126103758811951
NC4 NCC Mismatch: 0.08599999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0007591247558594
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 3.0414226055145264
Linear Weight Rank: 178
Intra Cos: 0.061884064227342606
Inter Cos: -0.004156863316893578
Norm Quadratic Average: 1.9212230443954468
Nearest Class Center Accuracy: 0.6215

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.4075510501861572
Linear Weight Rank: 4
Intra Cos: 0.2023717761039734
Inter Cos: -0.0020832999143749475
Norm Quadratic Average: 1.3037134408950806
Nearest Class Center Accuracy: 0.629

Output Layer:
Intra Cos: 0.22189632058143616
Inter Cos: 0.0015130614629015326
Norm Quadratic Average: 1.7670989036560059
Nearest Class Center Accuracy: 0.626

