Bad model deploying to GCP Cloudml

Question

I’m trying to deploy a model trained using Tensorflow 1.7 onto Google Cloud Platform. I get the following error:

Create Version failed. Bad model detected with error: "Failed to load model: Loading servable: {name: default version: 1} failed: Not found: Op type not registered 'SparseFillEmptyRows'\n\n (Error code: 0)"

I know Cloudml runtime prediction only supports Tensorflow 1.6 so I tried specifying:

REQUIRED_PACKAGES = [
  'tensorflow==1.6',
]

in setup.py but I still get the same message

Any help gratefully appreciated

So you want to use Tensorflow 1.7 and you're setting the version to 1.6 in your setup file ? Anyway...it looks like you're having a problem elsewhere... — ma3oun

MatthewScarpino MatthewScarpino · Accepted Answer · 2018-04-08T12:37:00

You need to rebuild your model using TensorFlow 1.6. You can't deploy a model created with TensorFlow 1.7 to the ML Engine.

Also, you can set the version of the engine's runtime to one of the versions listed here. If you're using gcloud ml-engine jobs submit training, you can set the version with the --runtime-version flag. The documentation is here.

Bad model deploying to GCP Cloudml

2 Answers