torchserve-dashboard

torchserve-dashboard copied to clipboard

stuff to check before update: https://github.com/pytorch/serve/pull/1421 https://github.com/pytorch/serve/blob/master/docs/request_envelopes.md

cceyda

Init status of Torchserve

2

Can I set the init status of Torchserve as start?

JiangongWang

Can't start torchserve-dashboard

1

I'm getting this error while on the start ``` Traceback (most recent call last): File "/home/kavan/.local/bin/torchserve-dashboard", line 5, in from torchserve_dashboard.cli import main File "/home/kavan/.local/lib/python3.8/site-packages/torchserve_dashboard/cli.py", line 2, in import streamlit.cli...

Kavan72

add methods to InferenceAPI

3

add get_predictions add get_explanations add get_workflow_predictions

FlorianMF

[WIP] Template for InferenceAPI

2

https://github.com/cceyda/torchserve-dashboard/issues/9 Just some brainstorming on how inference might work...

cceyda

Add custom HTTPClient class to be consumed by APIs

3

I created a separate HTTP Client class which the APIs consume. This way a (Management)API could take several clients or the same client be used by several APIs

FlorianMF

Mentioned in https://github.com/cceyda/torchserve-dashboard/issues/1 Model interpretability with Captum https://github.com/pytorch/serve/blob/master/captum/Captum_visualization_for_bert.ipynb This would be good to add if we end up adding an InferenceAPI

cceyda

Moving the discussion from https://github.com/cceyda/torchserve-dashboard/issues/1#issuecomment-863911194 to here Current challenges blocking this: - there is no way to know the format of the expected request/response. Especially for custom handlers. (I prefer...

cceyda

Docker container

3

I think it would be great for users and for developers to be able to easily share their dashboard or run it in production without deploying via Streamlit. I could...

FlorianMF