Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Local models not available when running cortex get for the TF predictor and when live-reloading is enabled #1554

Closed
RobertLucian opened this issue Nov 11, 2020 · 0 comments · Fixed by #1668
Closed

Local models not available when running cortex get for the TF predictor and when live-reloading is enabled #1554

RobertLucian opened this issue Nov 11, 2020 · 0 comments · Fixed by #1668
Assignees
@RobertLucian
Labels
bug Something isn't working
Milestone
v0.24

Comments

@RobertLucian
Copy link
Member

RobertLucian commented Nov 11, 2020 •
edited
Loading

Version

0.22

Description

When using a TensorFlow predictor and when live-reloading is enabled, local models that were passed in using the API spec, don't show up when running cortex get <api-name>.

- name: api
   kind: RealtimeAPI
   predictor:
     type: python
     model_path: ~/local-model/resnet50/
     ...

Consequence

No local model is accessible for inference.
@RobertLucian RobertLucian added the bug Something isn't working label Nov 11, 2020
@RobertLucian RobertLucian self-assigned this Dec 8, 2020
@RobertLucian RobertLucian changed the title Local models don’t show up when running cortex get for the TF predictor and when live-reloading is enabled Local models not available when running cortex get for the TF predictor and when live-reloading is enabled Dec 8, 2020
@RobertLucian RobertLucian mentioned this issue Dec 8, 2020
Merged
2 tasks
@deliahu deliahu added this to the v0.24 milestone Dec 8, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@RobertLucian RobertLucian

Labels
bug Something isn't working
Projects
None yet
Milestone
v0.24
Development

Successfully merging a pull request may close this issue.

Fix no local TF model accessible with LR enabled cortexlabs/cortex
2 participants
@deliahu @RobertLucian