-
Notifications
You must be signed in to change notification settings - Fork 1.2k
breaking: remove legacy TensorFlowModel and TensorFlowPredictor classes #1531
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
This change also removes the associated serialization/deserialization code used by TensorFlowPredictor and the locally copied TFS APIs.
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
AWS CodeBuild CI Report
Powered by github-codebuild-logs, available on the AWS Serverless Application Repository |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good to me
Issue #, if available:
#1462
Description of changes:
This change also removes the associated serialization/deserialization code used by TensorFlowPredictor and the locally copied TFS APIs.
Due to
sagemaker.tensorflow.serving.Model
not acceptingmodel_server_workers
, I ended up having to keep the TF-specifictransformer()
implementation, but I'd accidentally deleted the unit tests in #1510 (must've messed up my git branches), so that's why those are getting readded here.I'll move the
sagemaker.tensorflow.serving
classes to match the old class names/paths but I didn't want to do it in this PR in case it made the diff look unreadable.Testing done:
tox -e pylint,flake8,black-format --parallel all
pytest tests/unit/test_tf*
pytest tests/integ/test_tf*
Merge Checklist
Put an
x
in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.General
Tests
unique_name_from_base
to create resource names in integ tests (if appropriate)By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.