metaflow
metaflow copied to clipboard
Netflix
:rocket: Build and manage real-life ML, AI, and data science projects with ease!
Is that possible to get the value or `reserved_params` inside `FlowSpec` step? As for instance, how I can get the value of `max-workers` param if it is set or default...
I have "deployed" locally the metaflow service and now I would like to use a on-prem s3 storage for the artifacts. How should I configure it?
related to #467 When @resources specifies a float value, Metaflow throws a cryptic error ``` 'resources' and compute decorator have conflicting values for 'cpu'. Please use consistent values or specify...
We currently have read and write capabilities but do not support deleting. We could add a few calls like delete delete_all and some recursive way of deleting.
Currently, the code is packaged for Batch runs only. To be able to fully replicate and version things, it would be nicer if code was always stored as an artifact...
The code tarball saved by Metaflow is accessible with the client but it is not very easy to work with. We may want to make it more visible possibly even...
`S3(tmproot)` default to be `METAFLOW_ARTIFACT_LOCALROOT` if defined else `"."` see comment: https://github.com/Netflix/metaflow/pull/991#issuecomment-1097237329
[Note: currently in draft whilst a) I draft the code and b) check whether this resolves our situation - but would anyway appreciate feedback on whether the gist of this...
Logging when executing on batch is somewhat inconsistent. When executing a simple task, this is what prints out: ``` 2021-06-28 14:36:45.432 [7637/hello/92219 (pid 66823)] Task is starting. 2021-06-28 14:36:46.411 [7637/hello/92219...