aws / aws/amazon-sagemaker-feedback
Jumpstart includes a special character in the model name then prevents it from deploying
- Dominant language
- No language data
- Stars
- 10
- Forks
- 3
- PR merge metrics
- No merged PRs in 30d
Description
### Product Version
- [ ] Amazon SageMaker Studio Classic
- [ ] Amazon SageMaker Studio
- [X] Issue is not related to SageMaker Studio
### Issue Description
Open Jumpstart, select (for example)
SSD Efficientdet D0 512x512 COCO '17, by TensorFlow
and click deploy. With default settings, you now get the error message:
Failed to create endpoint1 validation error detected: Value 'ssd-efficientdet-d0-512x512-coco-'17-202308' at 'modelName' failed to satisfy constraint: Member must satisfy regular expression pattern: ^[a-zA-Z0-9]([\-a-zA-Z0-9]*[a-zA-Z0-9])?
This behavior did not exist four days ago. The reason is the apostrophe in the model name. I think also that the user cannot change it, so the user cannot work around it.
### Expected Behavior
_No response_
### Observed Behavior
_No response_
### Product Category
_No response_
### Feedback Category
_No response_
### Other Details
_No response_
Contributor guide
Research direction
Reproduce the failure in Amazon SageMaker JumpStart by selecting SSD Efficientdet D0 512x512 COCO '17 by TensorFlow and deploying with default settings. Start by tracing how the selected model name becomes the endpoint modelName, then verify that deployment succeeds for this model and that the resulting name satisfies the reported validation pattern.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws
- Domain
- cloud, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100