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_979323_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.870899677276611
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.848820686340332
Linear Weight Rank: 180
Intra Cos: 0.025354431942105293
Inter Cos: -0.00471116229891777
Norm Quadratic Average: 13.485132217407227
Nearest Class Center Accuracy: 0.592125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7868661880493164
Linear Weight Rank: 4
Intra Cos: 0.0418248176574707
Inter Cos: -0.009536892175674438
Norm Quadratic Average: 13.904169082641602
Nearest Class Center Accuracy: 0.8265

Output Layer:
Intra Cos: 0.5604466795921326
Inter Cos: -0.11661188304424286
Norm Quadratic Average: 7.6556854248046875
Nearest Class Center Accuracy: 0.981125

Test Set:
Average Loss: 0.6084481019973755
Accuracy: 0.7665
NC1 Within Class Collapse: 5.046144485473633
NC2 Equinorm: Features: 0.13153237104415894, Weights: 0.04063175246119499
NC2 Equiangle: Features: 0.14399387439092, Weights: 0.031023477514584858
NC3 Self-Duality: 0.5043767690658569
NC4 NCC Mismatch: 0.20199999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.870899677276611
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
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: 7.848820686340332
Linear Weight Rank: 180
Intra Cos: 0.023198194801807404
Inter Cos: -0.0033574504777789116
Norm Quadratic Average: 13.475086212158203
Nearest Class Center Accuracy: 0.6015

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7868661880493164
Linear Weight Rank: 4
Intra Cos: 0.030836109071969986
Inter Cos: -0.004681275226175785
Norm Quadratic Average: 13.894591331481934
Nearest Class Center Accuracy: 0.7245

Output Layer:
Intra Cos: 0.3680970072746277
Inter Cos: -0.05422036722302437
Norm Quadratic Average: 7.578769683837891
Nearest Class Center Accuracy: 0.7705

