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_338327_weight_decay_0.04.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5520291328430176
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.8347127437591553
Linear Weight Rank: 177
Intra Cos: 0.601231038570404
Inter Cos: 0.014410562813282013
Norm Quadratic Average: 1.8816393613815308
Nearest Class Center Accuracy: 0.979125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6899256706237793
Linear Weight Rank: 4
Intra Cos: 0.7501355409622192
Inter Cos: 0.024599812924861908
Norm Quadratic Average: 2.509714126586914
Nearest Class Center Accuracy: 0.98475

Output Layer:
Intra Cos: 0.8369417786598206
Inter Cos: 0.02492433786392212
Norm Quadratic Average: 4.514472484588623
Nearest Class Center Accuracy: 0.985875

Test Set:
Average Loss: 0.2669334697723389
Accuracy: 0.9865
NC1 Within Class Collapse: 3.0453319549560547
NC2 Equinorm: Features: 0.04200831055641174, Weights: 0.01537256594747305
NC2 Equiangle: Features: 0.4374011754989624, Weights: 0.4225173791249593
NC3 Self-Duality: 0.009132684208452702
NC4 NCC Mismatch: 0.024499999999999966

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.5520291328430176
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 2.8347127437591553
Linear Weight Rank: 177
Intra Cos: 0.6066792607307434
Inter Cos: 0.03360484912991524
Norm Quadratic Average: 1.8971879482269287
Nearest Class Center Accuracy: 0.976

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6899256706237793
Linear Weight Rank: 4
Intra Cos: 0.7478220462799072
Inter Cos: 0.05018502473831177
Norm Quadratic Average: 2.529411554336548
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.8392859101295471
Inter Cos: 0.05303662270307541
Norm Quadratic Average: 4.5431413650512695
Nearest Class Center Accuracy: 0.9825

