Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.129947662353516
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222442723810673
Norm Quadratic Average: 3.9938886165618896
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.104122161865234
Linear Weight Rank: 180
Intra Cos: 0.025405017659068108
Inter Cos: -0.004658774007111788
Norm Quadratic Average: 13.83342456817627
Nearest Class Center Accuracy: 0.591

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.95357346534729
Linear Weight Rank: 4
Intra Cos: 0.04072890058159828
Inter Cos: -0.009364196099340916
Norm Quadratic Average: 14.318643569946289
Nearest Class Center Accuracy: 0.82675

Output Layer:
Intra Cos: 0.5706443786621094
Inter Cos: -0.12097802013158798
Norm Quadratic Average: 8.01337718963623
Nearest Class Center Accuracy: 0.98725

Test Set:
Average Loss: 0.629774829864502
Accuracy: 0.7675
NC1 Within Class Collapse: 5.07774543762207
NC2 Equinorm: Features: 0.12992221117019653, Weights: 0.04071221128106117
NC2 Equiangle: Features: 0.14008822043736777, Weights: 0.03053375333547592
NC3 Self-Duality: 0.5168417692184448
NC4 NCC Mismatch: 0.20799999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.129947662353516
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.00454972218722105
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: 8.104122161865234
Linear Weight Rank: 180
Intra Cos: 0.023243451490998268
Inter Cos: -0.0033122538588941097
Norm Quadratic Average: 13.82668399810791
Nearest Class Center Accuracy: 0.6005

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.95357346534729
Linear Weight Rank: 4
Intra Cos: 0.02997181937098503
Inter Cos: -0.004700641613453627
Norm Quadratic Average: 14.320030212402344
Nearest Class Center Accuracy: 0.717

Output Layer:
Intra Cos: 0.3659895360469818
Inter Cos: -0.05820910632610321
Norm Quadratic Average: 7.933879375457764
Nearest Class Center Accuracy: 0.766

