about the learning rate for single GPU

[Amberrferr]

我想请问一下，根据get start.txt，config的optimizer中的学习率是根据8GPUS设置的，即Batch size为2的情况下，8GPUs的lr为0.01。为何get start.txt中说0.01对应的是4GPUS？ 如果我用的是单核GPU，那么我的学习率应该设置为0.00125还是0.0025呢？

[dingjiansw101]

The learning rate of SGD depends on the batch size. If your batch size is bs, then the lr = 0.01/8 * bs.

[Amberrferr]

The learning rate of SGD depends on the batch size. If your batch size is bs, then the lr = 0.01/8 * bs.

Okay, Thanks for you reply!