You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When training ResNet on ImageNet, the GluonCV uses a batchsize of 128x8GPUs with cosine learning rate. Do you have any suggestion to scale learning rate when using a small batchsize? I tried directly scaling down learning rate by the ratio of batchsize but it did not work very well.
Thanks.
The text was updated successfully, but these errors were encountered:
GluonCV use fp16 training, 128 batch size per gpu. You can use smaller batch size, but should be at least 256 for total mini-batch size to reproduce compatible performance.
When training ResNet on ImageNet, the GluonCV uses a batchsize of 128x8GPUs with cosine learning rate. Do you have any suggestion to scale learning rate when using a small batchsize? I tried directly scaling down learning rate by the ratio of batchsize but it did not work very well.
Thanks.
The text was updated successfully, but these errors were encountered: