aws / aws/aws-step-functions-data-science-sdk-python
ModelDataUrl is incorrect when result_path is defined in TrainingStep
- Dominant language
- Python
- Stars
- 299
- Forks
- 84
- PR merge metrics
- No merged PRs in 30d
Description
The ModelDataUrl in the Step Functions' defenition is '“ModelDataUrl.$“: “$[‘ModelArtifacts’][‘S3ModelArtifacts’]”' even though the result_path is defined in the TrainingStep, and it causes error like this.
> “An error occurred while executing the state ‘Save Model’ (entered at the event id #8). The JSONPath ’$[‘ModelArtifacts’][‘S3ModelArtifacts’]' specified for the field ‘ModelDataUrl.$’ could not be found in the input ...
It should be '“ModelDataUrl.$“: “$[‘TrainingStepResults’][‘ModelArtifacts’][‘S3ModelArtifacts’]”'.
```
training_step = steps.TrainingStep(
‘Model Training’,
estimator=tf_estimator,
data={
‘training’: inputs
},
job_name=execution_input[‘TrainingJobName’],
result_path=‘$.TrainingStepResults’,
wait_for_completion=True
)
model_step = steps.ModelStep(
‘Save Model’,
model=training_step.get_expected_model(),
model_name=execution_input[‘ModelName’],
instance_type=‘ml.m5.xlarge’,
result_path=‘$.ModelStepResults’
)
```
Contributor guide
Assessment
This issue has not been assessed yet.