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_314159_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.160841941833496
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.225225448608398
Linear Weight Rank: 179
Intra Cos: 0.027186991646885872
Inter Cos: -0.004283800721168518
Norm Quadratic Average: 14.044121742248535
Nearest Class Center Accuracy: 0.58925

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.799426317214966
Linear Weight Rank: 4
Intra Cos: 0.04308309033513069
Inter Cos: -0.008197896182537079
Norm Quadratic Average: 14.455991744995117
Nearest Class Center Accuracy: 0.79425

Output Layer:
Intra Cos: 0.5650772452354431
Inter Cos: -0.09230013191699982
Norm Quadratic Average: 7.729121685028076
Nearest Class Center Accuracy: 0.978875

Test Set:
Average Loss: 0.6320972537994385
Accuracy: 0.769
NC1 Within Class Collapse: 5.447658538818359
NC2 Equinorm: Features: 0.13989512622356415, Weights: 0.05001859739422798
NC2 Equiangle: Features: 0.13876744111378989, Weights: 0.03512084484100342
NC3 Self-Duality: 0.5971518754959106
NC4 NCC Mismatch: 0.25649999999999995

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.160841941833496
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549724515527487
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: 8.225225448608398
Linear Weight Rank: 179
Intra Cos: 0.026140708476305008
Inter Cos: -0.0036897696554660797
Norm Quadratic Average: 14.102316856384277
Nearest Class Center Accuracy: 0.581

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.799426317214966
Linear Weight Rank: 4
Intra Cos: 0.032183609902858734
Inter Cos: -0.0034489913377910852
Norm Quadratic Average: 14.494723320007324
Nearest Class Center Accuracy: 0.686

Output Layer:
Intra Cos: 0.3724842369556427
Inter Cos: -0.04399953782558441
Norm Quadratic Average: 7.575263500213623
Nearest Class Center Accuracy: 0.7595

