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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.960203170776367
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: 9.053717613220215
Linear Weight Rank: 179
Intra Cos: 0.17075785994529724
Inter Cos: 0.006146369967609644
Norm Quadratic Average: 5.5943989753723145
Nearest Class Center Accuracy: 0.9585

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.095841884613037
Linear Weight Rank: 4
Intra Cos: 0.6079388856887817
Inter Cos: 0.02794613316655159
Norm Quadratic Average: 7.0822882652282715
Nearest Class Center Accuracy: 0.972625

Output Layer:
Intra Cos: 0.7898778319358826
Inter Cos: 0.03985953703522682
Norm Quadratic Average: 18.133718490600586
Nearest Class Center Accuracy: 0.973625

Test Set:
Average Loss: 0.08470154929161072
Accuracy: 0.979
NC1 Within Class Collapse: 2.9883666038513184
NC2 Equinorm: Features: 0.03855336457490921, Weights: 0.01657702960073948
NC2 Equiangle: Features: 0.4345396359761556, Weights: 0.39372960726420086
NC3 Self-Duality: 0.05677145719528198
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.960203170776367
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: 9.053717613220215
Linear Weight Rank: 179
Intra Cos: 0.168051615357399
Inter Cos: 0.006594301201403141
Norm Quadratic Average: 5.602251052856445
Nearest Class Center Accuracy: 0.9525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.095841884613037
Linear Weight Rank: 4
Intra Cos: 0.6003589630126953
Inter Cos: 0.049311667680740356
Norm Quadratic Average: 7.152188777923584
Nearest Class Center Accuracy: 0.964

Output Layer:
Intra Cos: 0.7800642848014832
Inter Cos: 0.06676433980464935
Norm Quadratic Average: 18.313566207885742
Nearest Class Center Accuracy: 0.9665

