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_265358_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.918113708496094
Linear Weight Rank: 16
Intra Cos: 0.014583894982933998
Inter Cos: 0.004829855635762215
Norm Quadratic Average: 3.9931397438049316
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.955819129943848
Linear Weight Rank: 179
Intra Cos: 0.011977605521678925
Inter Cos: 0.002559895161539316
Norm Quadratic Average: 13.451741218566895
Nearest Class Center Accuracy: 0.466125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8116164207458496
Linear Weight Rank: 4
Intra Cos: 0.01542474515736103
Inter Cos: 0.0006290780147537589
Norm Quadratic Average: 13.925599098205566
Nearest Class Center Accuracy: 0.616125

Output Layer:
Intra Cos: 0.5386863350868225
Inter Cos: -0.03176291286945343
Norm Quadratic Average: 4.2511396408081055
Nearest Class Center Accuracy: 0.92675

Test Set:
Average Loss: 1.1689767417907715
Accuracy: 0.5525
NC1 Within Class Collapse: 15.018054962158203
NC2 Equinorm: Features: 0.015889568254351616, Weights: 0.023460468277335167
NC2 Equiangle: Features: 0.2579033374786377, Weights: 0.03713001559178034
NC3 Self-Duality: 1.0080807209014893
NC4 NCC Mismatch: 0.40700000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.918113708496094
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
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: 7.955819129943848
Linear Weight Rank: 179
Intra Cos: 0.012839899398386478
Inter Cos: 0.0027562857139855623
Norm Quadratic Average: 13.422965049743652
Nearest Class Center Accuracy: 0.4775

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8116164207458496
Linear Weight Rank: 4
Intra Cos: 0.010588577017188072
Inter Cos: 0.0015867191832512617
Norm Quadratic Average: 13.927567481994629
Nearest Class Center Accuracy: 0.5285

Output Layer:
Intra Cos: 0.15887556970119476
Inter Cos: 0.019315671175718307
Norm Quadratic Average: 4.059938907623291
Nearest Class Center Accuracy: 0.5545

