inference
AI
computer vision deployment
SHOW HN2023
71points
16comments
#854of 3,109 in 2023
Top 28%of 2023 by points
How HN took it
MixedNo clear lean
5 positive, 6 neutral or asking, 0 mixed, 3 critical, out of 14 comments about the project. Thread score +0.22.
Docs: 2 for, 2 againstIdea: 0 for, 1 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
Useful launch and tool, recommended by users
From 3 comments
Love & recommend Roboflow. Thanks for releasing this yall!
tlack on HNLooks great! Congrats on the launch.
pkiv on HNThis is sick
jvanillaaaa on HN
Video in README was impressive
From 1 comment
Thanks. The video blew my mind.
noman-land on HN
Objections
Unclear what the project is and why to use it, docs lacked WHY
From 2 comments
Interested, but after spending 2 min reading it I am still not sure what I am looking at exactly.
Aspos on HNGenuine feedback: I guess your readme.md describes the HOW well, but does not touch the WHY. Why should I use this? Why not?
Aspos on HN
Requires Roboflow API key to run
From 2 comments
Is it possible to run this without supplying Roboflow API key? Why the requirement?
thangngoc89 on HNYes, but also not easily right now. We’ll be adding more supported ways to load models soon, but right now things largely assume using our model registry (and API Key is how it…
yeldarb on HN
Requests
Add images or video to README
From 1 comment
Looks interesting. Missing a trick by not having some images in the README though. Especially since this post here is where I found out it can run CLIP instead of the readme.
nl on HN
Support running without Roboflow API key
From 1 comment
Is it possible to run this without supplying Roboflow API key? Why the requirement?
thangngoc89 on HN
Questions
How does it compare to NVIDIA Triton?
From 1 comment
How does this compare to Nvidia Triton? It's also a dockerized inference server capable of running ONNX, TRT, and many other compiled models. Automatic request queuing, HTTP &…
claytonjy on HN
Alternatives named
NVIDIA Triton
From 2 comments
How does this compare to Nvidia Triton? It's also a dockerized inference server capable of running ONNX, TRT, and many other compiled models. Automatic request queuing, HTTP &…
claytonjy on HNInference operates at a higher layer of abstraction (tasks & architectures vs weights), targets a different audience (software engineers vs deep machine learning experts), and is…
yeldarb on HN
DeepStream
From 1 comment
We'll work on adding this to the repo, but I'll try to summarize here. Why should I use this? If you're looking to deploy computer vision models to production (on edge devices or…
yeldarb on HN