Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0466840267181396
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584841698408127
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 3.3037378787994385
Linear Weight Rank: 177
Intra Cos: 0.48826029896736145
Inter Cos: 0.010728009976446629
Norm Quadratic Average: 2.173776626586914
Nearest Class Center Accuracy: 0.979

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.851991653442383
Linear Weight Rank: 4
Intra Cos: 0.7342723608016968
Inter Cos: 0.020035453140735626
Norm Quadratic Average: 2.8347127437591553
Nearest Class Center Accuracy: 0.984625

Output Layer:
Intra Cos: 0.8327814936637878
Inter Cos: 0.014563966542482376
Norm Quadratic Average: 5.3621368408203125
Nearest Class Center Accuracy: 0.9855

Test Set:
Average Loss: 0.22328018760681154
Accuracy: 0.988
NC1 Within Class Collapse: 2.702660083770752
NC2 Equinorm: Features: 0.041188739240169525, Weights: 0.01424543745815754
NC2 Equiangle: Features: 0.4358610312143962, Weights: 0.4170883496602376
NC3 Self-Duality: 0.013131409883499146
NC4 NCC Mismatch: 0.020499999999999963

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.0466840267181396
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 3.3037378787994385
Linear Weight Rank: 177
Intra Cos: 0.4851232171058655
Inter Cos: 0.024754459038376808
Norm Quadratic Average: 2.188673734664917
Nearest Class Center Accuracy: 0.9735

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.851991653442383
Linear Weight Rank: 4
Intra Cos: 0.7289499640464783
Inter Cos: 0.040612250566482544
Norm Quadratic Average: 2.8592090606689453
Nearest Class Center Accuracy: 0.9805

Output Layer:
Intra Cos: 0.8262913823127747
Inter Cos: 0.03987671807408333
Norm Quadratic Average: 5.398746490478516
Nearest Class Center Accuracy: 0.984

