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_846264_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.5823540687561035
Linear Weight Rank: 16
Intra Cos: 0.07988917082548141
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: 6.707971572875977
Linear Weight Rank: 179
Intra Cos: 0.2172292172908783
Inter Cos: 0.004516934510320425
Norm Quadratic Average: 4.196796417236328
Nearest Class Center Accuracy: 0.968

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6023871898651123
Linear Weight Rank: 4
Intra Cos: 0.6587035059928894
Inter Cos: 0.03342706710100174
Norm Quadratic Average: 5.057281970977783
Nearest Class Center Accuracy: 0.975125

Output Layer:
Intra Cos: 0.7964897155761719
Inter Cos: 0.04356513172388077
Norm Quadratic Average: 11.698634147644043
Nearest Class Center Accuracy: 0.97525

Test Set:
Average Loss: 0.11668710947036744
Accuracy: 0.9805
NC1 Within Class Collapse: 2.7513656616210938
NC2 Equinorm: Features: 0.03840358182787895, Weights: 0.016827594488859177
NC2 Equiangle: Features: 0.43410253524780273, Weights: 0.4030637741088867
NC3 Self-Duality: 0.038775600492954254
NC4 NCC Mismatch: 0.03149999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.5823540687561035
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: 6.707971572875977
Linear Weight Rank: 179
Intra Cos: 0.21420122683048248
Inter Cos: 0.009526599198579788
Norm Quadratic Average: 4.206126689910889
Nearest Class Center Accuracy: 0.9615

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6023871898651123
Linear Weight Rank: 4
Intra Cos: 0.6512897610664368
Inter Cos: 0.056183625012636185
Norm Quadratic Average: 5.107398986816406
Nearest Class Center Accuracy: 0.97

Output Layer:
Intra Cos: 0.7881145477294922
Inter Cos: 0.07003121078014374
Norm Quadratic Average: 11.806086540222168
Nearest Class Center Accuracy: 0.971

