wy1iu / LargeMargin_Softmax_Loss

Implementation for <Large-Margin Softmax Loss for Convolutional Neural Networks> in ICML'16.
Other
350 stars 115 forks source link

Is the CIFAR10 dataset error rate given in the paper the result of a single model? #33

Open lyl120117 opened 1 year ago

lyl120117 commented 1 year ago

@wy1iu I tried to reproduce L-Softmax with pytorch, the CIFAR10 dataset best error rate is 10.5 when m=2, higher than 7.73 in the paper, I would like to know if the 7.73 error rate is the result of a single model, or if multiple models are integrated? I am looking forward to your reply, thanks.