Fixing issue #85 torch-model-archiver skips other other model artefacts

aws / sagemaker-pytorch-inference-toolkit

Toolkit for allowing inference and serving with PyTorch on SageMaker. Dockerfiles used for building SageMaker Pytorch Containers are at https://github.com/aws/deep-learning-containers.

Apache License 2.0

134 stars 70 forks source link

Fixing issue #85 torch-model-archiver skips other other model artefacts #94

Open amaharek opened 3 years ago

amaharek commented 3 years ago

*Issue # 85

Description of changes: torch-model-archiver skips model files in model.tar.gz except model.pth

This issue makes all pytorch inference containers >= 1.6 fails to launch models with multiple files in model.tar.gz.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

sagemaker-bot commented 3 years ago

AWS CodeBuild CI Report

CodeBuild project: sagemaker-pytorch-inference-toolkit-pr
Commit ID: 1ccc481add743c01c35763a654f365d4ec2a11dc
Result: FAILED
Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

sagemaker-bot commented 3 years ago

AWS CodeBuild CI Report

CodeBuild project: sagemaker-pytorch-inference-toolkit-pr
Commit ID: b638c60c826f7a46016d4957aa1e19508cfbb145
Result: FAILED
Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository