TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Benchmarking the Major Cloud Vision AutoML Tools

29 pointsby rocaucalmost 5 years ago

5 comments

RcouF1uZ4gsCalmost 5 years ago
This is amazing content marketing, similar to Backblaze hard drive stats.<p>It was well-written and very informative. I enjoyed reading it and learned something new and potentially useful. And it brought attention to a potential pain point (trying to train and infer models on multiple platforms) and suggested their product to help(roboflow). It got the marketing message across without being irritating or obtrusive. A win-win situation for both reader and company.<p>Again, great writeup. I wish more content marketing would be this engaging and useful.
评论 #23981388 未加载
评论 #23981392 未加载
mlthoughts2018almost 5 years ago
The thing with evaluating these services is that business people or product managers don’t understand that accuracy on benchmarks doesn’t map well to accuracy on <i>your</i> problem. If you have a wacky data distribution (hint: you do), say like a collection of photos all taken inside the same building, you can’t generalize to consider benchmark stats.<p>On top of this, these services charge you for usage, not for <i>accurate</i> usage. This is a major issue that so many people overlook.<p>What does it matter if it’s cheap per request? That only helps you if accuracy per request is very high. Otherwise you’re paying for cheap garbage, or in some use cases you must grow requests much larger to overcome errors per request, like if you’re trying to get a bulk of labeled data via these services.<p>Most use cases are still better off hiring ML engineers who understand how to evaluate accuracy for the unique business use case, fine tune or train a model, and do it in house (or at least give you deep assurances of the rare cases when the big cloud services actually are cost effective to use).<p>For most use cases, you’re wasting your money trying for ML-as-a-service like this.
评论 #23981407 未加载
yeldarbalmost 5 years ago
Biggest surprise for me was that they can’t train on COCO. Would have thought their performance would be a major part of the marketing considering how prominent that benchmark is in the research community.
评论 #23981188 未加载
kuzeealmost 5 years ago
Just learned a lot about the different hosted ML options, thanks for the write-up with backing data. How much did this cost you overall?
评论 #23981280 未加载
joramsalmost 5 years ago
I think there&#x27;s a number missing under Google Cloud AutoML Vision Inference Cost:<p>&gt; Our tests yielded x predictions per second