Google AI Platform is a managed service that enables to easily build machine learning models. AI Platform service is integrated with Google Cloud Dataflow, Google Cloud Storage, and Google BigQuery.
Questions tagged [google-ai-platform]
205 questions
15
votes
3 answers
Kubeflow vs Vertex AI Pipelines
I was exploring kubeflow pipelines and Vertex AI pipelines. From what I understand, Vertex AI pipelines is a managed version of kubeflow pipelines so one doesn't need to deploy a full fledged kubeflow instance. In that respect, pricing aside, Vertex…
racerX
- 930
- 9
- 25
9
votes
2 answers
Vertex AI prediction - Autoscaling cannot set minimum node to 0
I am unclear abut Vertex AI pricing for model predictions. In the documentation, under the heading More about automatic scaling of prediction nodes one of the points mentioned is:
"If you choose automatic scaling, the number of nodes…
racerX
- 930
- 9
- 25
7
votes
1 answer
HttpError 403 with CONSUMER_INVALID as the reason when deploying a machine learning model to Google cloud's AI platform
I am following the tutorial here (https://cloud.google.com/ai-platform/training/docs/training-jobs#python_1) and using Python to deploy a machine learning model to Google cloud for training. However, I got HttpError 403: "Permission denied on…
Xi Liu
- 559
- 9
- 18
6
votes
2 answers
Google Cloud Vertex AI with Golang: rpc error: code = Unimplemented desc = unexpected HTTP status code received from server: 404 (Not Found)
I have a Vertex AI model deployed on an endpoint and want to do some prediction from my app in Golang.
To do this I create code inspired by this example :…
garrym
- 61
- 4
6
votes
1 answer
Vertex AI custom container batch prediction
I have created a custom container for prediction and successfully uploaded the model to Vertex AI. I was also able to deploy the model to an endpoint and successfully request predictions from the endpoint. Within the custom container code, I use the…
racerX
- 930
- 9
- 25
6
votes
2 answers
Google Kubernetes Engine vs Vertex AI (AI Platform Unified) for Serving Model Prediction
With Google releasing Vertex AI lately that integrates all its MLOps platforms, I wonder what would be the difference in serving a custom trained PyTorch/Tensorflow model on GKE vs Vertex AI (or AI Platform Unified, since the rebranding just took…
Andrew
- 73
- 1
- 5
6
votes
0 answers
GCP AI Platform job is stuck
I'm running a job on AI Platform and it's running for over an hour with no progress, no results, no logs(only few logs showing it's running)
Here is the region, machine type, gpus I was using:
"region": "us-central1",
"runtimeVersion": "2.2",
…
Kevin H
- 61
- 1
5
votes
2 answers
cannot import name 'WKBWriter' from 'shapely.geos' when import google cloud ai platform
When I run this code on google colab.
from google.cloud import aiplatform
The following error occurred
ImportError: cannot import name 'WKBWriter' from 'shapely.geos' (/usr/local/lib/python3.8/dist-packages/shapely/geos.py)
Does anyone know how to…
47jeff
- 53
- 1
- 4
5
votes
1 answer
How to install lightgbm on custom prediction routine?
I have trained a LightGBM model and now want to create a custom prediction routine for deployment on google aiplatform.
While loading model file, its throws an error that lightgbm is not installed.
I used below code in setup.py but its not…
kanav anand
- 411
- 1
- 4
- 14
5
votes
1 answer
Training using object detection api is not running on GPUs in AI Platform
I am trying to run the training of some models in tensorflow 2 object detection api.
I am using this command:
gcloud ai-platform jobs submit training segmentation_maskrcnn_`date +%m_%d_%Y_%H_%M_%S` \
--runtime-version 2.1 \
--python-version…
sniper71
- 479
- 1
- 4
- 16
5
votes
0 answers
Error creating version google cloud ai-platform. ImportError: cannot import name 'collections_abc' from 'six.moves' (unknown location)
I'm trying to deploy a model version in google cloud ai-platform.
I successfully create the model (called MyModel), but when I try to deploy a version of the model from the command line, it prompts the next error:
Create Version failed. Bad model…
5
votes
2 answers
Unable to deploy with custom container GCP
My image is 11.4 GB. I'm trying the following command:
gcloud beta ai-platform versions create v1 \
--region=$REGION \
--model=$MODEL \
--machine-type=n1-highmem-2 \
--image=$REGION-docker.pkg.dev/$PROJECT_ID/$REPO_NAME/$IMAGE_NAME \
…
gkv
- 360
- 1
- 8
5
votes
2 answers
Google cloud AI platform jupyter notebook instance will not open even after a reset and is running
I am using the Google AI platform which provides jupyterlab notebooks. I have 2 notebook instances set up to run R of which only one notebook now opens. The first notebook will not open regardless of the number of stops and resets I performed. The…
Vass
- 2,682
- 13
- 41
- 60
5
votes
2 answers
How to log from a custom ai platform model
I recently deployed a custom model to google cloud's ai-platform, and I am trying to debug some parts of my preprocessing logic. However, My print statements are not being logged to the stackdriver output. I have also tried using the logging client…
Nikita Jerschow
- 836
- 2
- 11
- 24
4
votes
1 answer
Specify signature name on Vertex AI Predict
I've deployed a tensorflow model in vertex AI platform using TFX Pipelines. The model have custom serving signatures but I'm strugling to specify the signature when I'm predicting.
I've the exact same model deployed in GCP AI Platform and I'm able…
