CynthiaProtector opened a new issue #15962: ResNet18_v2 under the directory of /mxnet/example/gluon URL: https://github.com/apache/incubator-mxnet/issues/15962 I tried to train _ResNet18_v2_ with CIFAR-10, the initial learning rate is 0.1, and decrease to 0.01 and 0.001 at the 80 epoch and 160 epoch (The _image_classification.py_ doest not implement the lr_scheduler function and I add that myself). Even training on a single node with 4 GPUs, the final test accuracy is around 81%, why is that?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
