The TensorFlow Cloud repository provides APIs that will allow to easily go from debugging and training your Keras and TensorFlow code in a local environment to distributed training in the cloud.
Thank you so much for raising this! this is definitely high on our radar. At the same time if you or anybody else is interested to pick this this please let us know.
Currently, job sent to AI Platform is always as specified in function
get_region()
: https://github.com/tensorflow/cloud/blob/8644935271ffa4cc86f6be7d7af8f905d097cea4/src/python/tensorflow_cloud/core/gcp.py#L73It would be useful if the user could specify the region, e.g. as a parameter in
tfc.run
.