Google Cloud ML Engine is a managed, scalable service that enables building and training of machine learning models in the cloud as part of the Google Cloud suite of products: including TensorFlow, storage, BigQuery, Dataflow and others.
Questions tagged [google-cloud-ml-engine]
185 questions
0
votes
1 answer
High latency issue of online prediction
I've deployed a linear model for classification on Google Machine Learning Engine and want to predict new data using online prediction.
When I called the APIs using Google API client library, it took around 0.5s to get the response for a request…
tintn
- 1
- 2
0
votes
1 answer
Error Uploading data to deployed model for prediction from appengine. works fine from local system
I am facing problem Uploading data from appengine to deployed model for prediction. The function works fine from my local system, But when I deploy the application I get some error saying that data is not Json Serializable.I don't understand this…
Akhil_Singh_Rana
- 355
- 1
- 2
- 10
0
votes
1 answer
Prediction failed: unknown error
I'm using Google Cloud Machine Learning to predict images with labels.
I've trained my model, named flower and I see the API end point at Google API Exporer but, when I call the API at API Explorer, I get the following error:
Image Error
I can't…
Ibere Spadoto
- 171
- 13
0
votes
2 answers
CloudML job + verbosity == Error
Runnning the dataeng-machine-learning codelab on step 9. 4. Feature Engineering.
The notebook step for running a tarin job is:
%%bash
OUTDIR=gs://${BUCKET}/taxifare/ch4/taxi_trained
JOBNAME=lab4a_$(date -u +%y%m%d_%H%M%S)
echo $OUTDIR $REGION…
srfrnk
- 2,459
- 1
- 17
- 32
0
votes
1 answer
Memory Leak in TensorFlow Google Cloud ML Training
I've been trying the TensorFlow tutorial scripts on Google Cloud ML.
In particular I've used the cifar10 CNN tutorial scripts at https://github.com/tensorflow/models/tree/master/tutorials/image/cifar10.
When I run this training script in Google…
Chris
- 183
- 1
- 10
0
votes
0 answers
Model uploaded to Cloud ML Engine won't create version, but runs locally
I've trained a model that I want to serve in Google Cloud ML Engine. I've exported it using the SavedModel format required and tested it using the following:
gcloud ml-engine local predict --model-dir=saved/ --json-instances=one-record.json
The…
Mark McDonald
- 7,571
- 6
- 46
- 53
0
votes
1 answer
How to use Google Natural Language Processing Cloud API in Android
Hello I guys I want to use Google's Natural Language Processing Cloud API for my android Application. What are the steps for getting the reference to the api and what all things is to be downloaded and what are the steps to be followed
Jai
- 3,211
- 2
- 17
- 26
0
votes
1 answer
Missing dependency for local prediction: No module named ml.prediction
Running
gcloud ml-engine local predict \
--model-dir=... \
--text-instances=... \
--verbosity=debug
throws a No module named ml.prediction error.
gcloud --version
Google Cloud SDK 155.0.0
nkconnor
- 672
- 3
- 18
0
votes
0 answers
kenlm.Model' object has no attribute 'score' while running on google cloud ML
AttributeError: 'kenlm.Model' object has no attribute 'score'
>>> model = kenlm.Model('LM/en.europarl-nc.lm')
>>> model.score('This is a test')
Traceback (most recent call last):
File "", line 1, in
AttributeError:…
Appu
- 83
- 9
0
votes
3 answers
local predict on the google cloud ml census sample
I successfully train my https://github.com/GoogleCloudPlatform/cloudml-samples/tree/master/census model/experiment both locally and in the cloud. And I'm able to deploy my sample and run predictions in the cloud.
But if I wanted to run my…
yarc68000
- 15
- 5
0
votes
3 answers
Why am I getting an "Error loading notebook" error when trying to set up Datalab and do image classification on Cloud ML Engine?
I am following the tutorial here:
https://codelabs.developers.google.com/codelabs/cloud-ml-engine-image-classification/index.html?index=..%2F..%2Findex#0
and it is claiming that it will allow me to do image classification on the google cloud. I…
sometimesiwritecode
- 2,993
- 7
- 31
- 69
0
votes
1 answer
Why is ml-engine functions present in Google Client API library instead of Google Cloud client library?
https://cloud.google.com/ml-engine/docs/tutorials/python-guide says ml-engine library in present in Google Client API library. Since Google Cloud client library is tailor-made for cloud applications, it should have had it no?
0
votes
1 answer
How to use TCMalloc on Google Cloud ML Engine
How to use TCMalloc on Google Cloud ML Engine? Or apart from TCMalloc, is there any other way to solve memory leak issues on ML Engine?
Finalizing graph doesn't seem to help.
Memory utilization graph:
I've got out of memory error after training 73…
Fei
- 23
- 4
0
votes
2 answers
The user doesn't have the required permission ml.versions.predict on the resource (Cloud ML Engine)
I have a service account that I have given Viewer role, and have downloaded the credentials json file and set the correct environment variable for it. I am trying to run the example here:
def predict_json(project, model, instances, version=None):
…
Andrew
- 6,295
- 11
- 56
- 95
0
votes
1 answer
Google ML - Can't read data off Google cloud bucket
I've followed these instructions from here to get my data being read from a google storage bucket by the google ML engine. - https://cloud.google.com/ml-engine/docs/how-tos/working-with-data
But cannot seem to get my code to read from the bucket…
vr9494
- 76
- 6