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_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.793237209320068
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: 7.9312567710876465
Linear Weight Rank: 179
Intra Cos: 0.1901426613330841
Inter Cos: 0.010255136527121067
Norm Quadratic Average: 4.924680709838867
Nearest Class Center Accuracy: 0.962125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.852295160293579
Linear Weight Rank: 4
Intra Cos: 0.6361008286476135
Inter Cos: 0.028601134195923805
Norm Quadratic Average: 6.012933254241943
Nearest Class Center Accuracy: 0.977625

Output Layer:
Intra Cos: 0.8034228682518005
Inter Cos: 0.03634297475218773
Norm Quadratic Average: 14.581621170043945
Nearest Class Center Accuracy: 0.978875

Test Set:
Average Loss: 0.09366169381141663
Accuracy: 0.9785
NC1 Within Class Collapse: 2.844125509262085
NC2 Equinorm: Features: 0.043724220246076584, Weights: 0.012984341941773891
NC2 Equiangle: Features: 0.4336610237757365, Weights: 0.3907734553019206
NC3 Self-Duality: 0.05432493984699249
NC4 NCC Mismatch: 0.025499999999999967

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.793237209320068
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: 7.9312567710876465
Linear Weight Rank: 179
Intra Cos: 0.18717795610427856
Inter Cos: 0.009425175376236439
Norm Quadratic Average: 4.933534622192383
Nearest Class Center Accuracy: 0.957

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.852295160293579
Linear Weight Rank: 4
Intra Cos: 0.6295190453529358
Inter Cos: 0.026722775772213936
Norm Quadratic Average: 6.070752143859863
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.7916817665100098
Inter Cos: 0.029366955161094666
Norm Quadratic Average: 14.705707550048828
Nearest Class Center Accuracy: 0.978

