Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.060648918151855
Linear Weight Rank: 16
Intra Cos: 0.014583897776901722
Inter Cos: 0.004829857032746077
Norm Quadratic Average: 3.9931399822235107
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.110191345214844
Linear Weight Rank: 179
Intra Cos: 0.012492685578763485
Inter Cos: 0.004807592369616032
Norm Quadratic Average: 13.829365730285645
Nearest Class Center Accuracy: 0.466375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8514773845672607
Linear Weight Rank: 4
Intra Cos: 0.016125906258821487
Inter Cos: 0.0003447365015745163
Norm Quadratic Average: 14.238823890686035
Nearest Class Center Accuracy: 0.622875

Output Layer:
Intra Cos: 0.5590015649795532
Inter Cos: -0.01933131366968155
Norm Quadratic Average: 4.2724175453186035
Nearest Class Center Accuracy: 0.93

Test Set:
Average Loss: 1.1960930862426757
Accuracy: 0.5515
NC1 Within Class Collapse: 14.843401908874512
NC2 Equinorm: Features: 0.06158366799354553, Weights: 0.00867293681949377
NC2 Equiangle: Features: 0.2288090387980143, Weights: 0.045846447348594666
NC3 Self-Duality: 1.0171107053756714
NC4 NCC Mismatch: 0.39449999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.060648918151855
Linear Weight Rank: 16
Intra Cos: 0.014108890667557716
Inter Cos: 0.005012288689613342
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.110191345214844
Linear Weight Rank: 179
Intra Cos: 0.012267793528735638
Inter Cos: 0.004121727310121059
Norm Quadratic Average: 13.766627311706543
Nearest Class Center Accuracy: 0.4685

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8514773845672607
Linear Weight Rank: 4
Intra Cos: 0.010431692004203796
Inter Cos: 0.0010639613028615713
Norm Quadratic Average: 14.20669174194336
Nearest Class Center Accuracy: 0.531

Output Layer:
Intra Cos: 0.16074571013450623
Inter Cos: 0.03377171605825424
Norm Quadratic Average: 4.1461029052734375
Nearest Class Center Accuracy: 0.539

