my_ml_service
Learning and science
tutorial
SHOW HN2020
67points
22comments
#895of 3,028 in 2020
Top 30%of 2020 by points
How HN took it
CuriousMostly questions and neutral comments
1 positive, 4 neutral or asking, 0 mixed, 3 critical, out of 8 comments about the project. Thread score -0.18.
Design: 1 for, 3 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Django admin panel gives UI without extra coding
From 1 comment
You are right! I like Django admin panel, without coding you get UI and I'm comfortable with Django + DRF. In Flask you need to add many things to make it usable. If you check…
pplonski86 on HN
Objections
Flask is simpler and lighter for a REST model endpoint
From 1 comment
Why use Django when Flask is so much simpler and has less overhead? For just a REST ML model endpoint, Flask does everything you need, and no more. It's a perfect fit.
VHRanger on HN
Running models inside views blocks requests under load
From 2 comments
Calling the ML model should be done via Django Channels or a similar background queue and not directly within the view (request handler) as if the inputs/inference is too big, it…
ampdepolymerase on HNI agree. The ML Algorithms and models can run into huge sizes. I have one with half a gig of serialised model, when running takes up close to 3.5 Gigs. This approach of directly…
tecoholic on HN
Requests
Add background processing for large models
From 1 comment
It really depends. For sure there are models which should be processed in the background. It is a very basic tutorial that shows how simple ML models can be used as REST API. In…
pplonski86 on HN
Questions
Why CharField with max_length 10K instead of TextField
From 1 comment
I noticed that the models use CharField with a max_length of 10K. Why not use TextField?
tecoholic on HN
Alternatives named
Gradio
From 1 comment
[Gradio](gradio.app) can save a lot of time to serve the same purpose - making it super easy to serve any python based ML. It provides dozens of interface components, including…
Aliabid94 on HN
inferrd
From 1 comment
For anyone looking to deploy ML models a little bit easier, check out https://inferrd.com It's a simple drag and drop to deploy tensorflow, scikit, spacy, keras or pytorch.
theo31 on HN
deepserve.ai
From 1 comment
For anyone who is looking to make deploying ML models easier, I created https://deepserve.ai You can run `deepserve deploy` on the command line and it will stand up a REST…
jeffrwells on HN
FastAPI
From 1 comment
May be Op wanted to take the advantage of batteries included features like, admin panel, templates etc. Or is just very comfortable with django. If we are talking speed and…
anaganisk on HN