search

weiaicunzai / Bag_of_Tricks_for_Image_Classification_with_Convolutional_Neural_Networks

experiments on Paper <Bag of Tricks for Image Classification with Convolutional Neural Networks> and other useful tricks to improve CNN acc
714 stars 123 forks source link

About learning rate #9

Open Zoe-Wan opened 2 years ago

Zoe-Wan commented 2 years ago

I wonder how much the value of the base learning rate you use when batch size is 256? I have tried 0.1 ( as the figure 3 of the paper suggests ) , but got a bad consequence. I find that in your code the default value of the learning rate is 0.04, does it work?

liuhh02 commented 2 years ago

Yes, the README.md mentions that using a learning rate of 0.04 with batch size 256 yielded an accuracy of 71.21%, which is 6.61% higher than the baseline accuracy of 64.60%.