Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Hey Guys! I Was Wondering If There Are Any Good Examples In Deployment Of Cv (Detection) Models Through Clearml-Serving? The Examples I Have Seen So Far Are Classification, And So The Post-Processing From The Triton Output Is Minimal. As An Example Mayb

Hey guys!

I was wondering if there are any good examples in deployment of CV (detection) models through ClearML-serving? The examples I have seen so far are classification, and so the post-processing from the triton output is minimal.

As an example maybe the Yolo models (given that they had advertised good integration with ClearML).

It would be awesome to be able to utilize the ClearML stack end-to-end all the way to deployment!

Posted one year ago
Votes Newest

Answers 3

Well, that's what open source is for 😉 code borrowing is like 90% of the job of software engineers 😄

Posted one year ago

Thanks for the pointers! Yes we are expecting an uphill struggle trying to get it to work haha. The output of a computer vision detection model is quite monsterous (especially since I do not understand all of it!). We will probably have to rely on a lot of code-borrowing from the yolo repositories haha.

Posted one year ago

That's a good idea! I think the YOLO models would be a great fit for a tutorial/example like this. We can add it to our internal list of TODOs, or if you want, you could take a stab at it and we'll try to support you through it 🙂 It might take some engineering though! Serving is never drag and drop 🙂

That said, I think it should be quite easy to do since YOLOv8 supports exporting to tensorrt format, which is native to Triton serving which underlies ClearML serving. So the process should be very similar to this blogpost .

Posted one year ago
3 Answers
one year ago
one year ago