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_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.2800559997558594
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: 2.573878526687622
Linear Weight Rank: 175
Intra Cos: 0.6654855012893677
Inter Cos: 0.018543193116784096
Norm Quadratic Average: 1.7122429609298706
Nearest Class Center Accuracy: 0.980875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.5594823360443115
Linear Weight Rank: 4
Intra Cos: 0.7556073665618896
Inter Cos: 0.02383457124233246
Norm Quadratic Average: 2.2722909450531006
Nearest Class Center Accuracy: 0.981875

Output Layer:
Intra Cos: 0.8361178636550903
Inter Cos: 0.0246441587805748
Norm Quadratic Average: 3.917924404144287
Nearest Class Center Accuracy: 0.982875

Test Set:
Average Loss: 0.310623610496521
Accuracy: 0.9885
NC1 Within Class Collapse: 4.324293613433838
NC2 Equinorm: Features: 0.04064415767788887, Weights: 0.016013002023100853
NC2 Equiangle: Features: 0.43940019607543945, Weights: 0.42848185698191327
NC3 Self-Duality: 0.006543765775859356
NC4 NCC Mismatch: 0.025000000000000022

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.2800559997558594
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: 2.573878526687622
Linear Weight Rank: 175
Intra Cos: 0.6742827892303467
Inter Cos: 0.03601260110735893
Norm Quadratic Average: 1.7276456356048584
Nearest Class Center Accuracy: 0.973

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.5594823360443115
Linear Weight Rank: 4
Intra Cos: 0.7513453364372253
Inter Cos: 0.04914548993110657
Norm Quadratic Average: 2.289752244949341
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.831314742565155
Inter Cos: 0.0516866073012352
Norm Quadratic Average: 3.9416370391845703
Nearest Class Center Accuracy: 0.9795

