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_265358_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.183210372924805
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.136073112487793
Linear Weight Rank: 180
Intra Cos: 0.029848642647266388
Inter Cos: -0.004084313753992319
Norm Quadratic Average: 13.866236686706543
Nearest Class Center Accuracy: 0.59725

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9115328788757324
Linear Weight Rank: 4
Intra Cos: 0.042421843856573105
Inter Cos: -0.010174524039030075
Norm Quadratic Average: 14.326759338378906
Nearest Class Center Accuracy: 0.82425

Output Layer:
Intra Cos: 0.576884925365448
Inter Cos: -0.12963560223579407
Norm Quadratic Average: 7.908452033996582
Nearest Class Center Accuracy: 0.98725

Test Set:
Average Loss: 0.635667465209961
Accuracy: 0.765
NC1 Within Class Collapse: 5.134545803070068
NC2 Equinorm: Features: 0.10996180772781372, Weights: 0.04066364839673042
NC2 Equiangle: Features: 0.11805933713912964, Weights: 0.031799341241518654
NC3 Self-Duality: 0.5386568903923035
NC4 NCC Mismatch: 0.22199999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.183210372924805
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: 8.136073112487793
Linear Weight Rank: 180
Intra Cos: 0.02671871706843376
Inter Cos: -0.004038006067276001
Norm Quadratic Average: 13.8778657913208
Nearest Class Center Accuracy: 0.6

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9115328788757324
Linear Weight Rank: 4
Intra Cos: 0.03193842992186546
Inter Cos: -0.006320599466562271
Norm Quadratic Average: 14.34760570526123
Nearest Class Center Accuracy: 0.718

Output Layer:
Intra Cos: 0.3611736595630646
Inter Cos: -0.07208102941513062
Norm Quadratic Average: 7.753216743469238
Nearest Class Center Accuracy: 0.765

