search

tensorflow / adanet

Fast and flexible AutoML with learning guarantees.
https://adanet.readthedocs.io
Apache License 2.0
3.47k stars 527 forks source link

How to run on multiple GPUs? #108

Open marsggbo opened 5 years ago

marsggbo commented 5 years ago

Could you share some example codes that can run on multiple GPUs?

cweill commented 5 years ago

@marsggbo: For multiple GPUs on the same machine depends on https://github.com/tensorflow/adanet/issues/87 being fixed first. However, you can distribute training across multiple machines each with one GPU using TF_CONFIG: https://cloud.google.com/ml-engine/docs/tensorflow/distributed-training-details

You can also look at https://github.com/tensorflow/adanet/tree/master/research/improve_nas to see how we ran some experiments on Google Cloud with multiple GPUs.

gargprince1702 commented 5 years ago

@marsggbo: For some examples of multiple GPUs clink on the below link I think that helps you :) https://jhui.github.io/2017/03/07/TensorFlow-GPU/