Deepchecks Testing Package - Open source tool for testing & validating your model & data

Find problems in your ML models and data before it’s too late!
With just a few lines of code, Deepchecks creates elaborate reports about your data’s integrity, distributions, and your model’s performance.

Add a comment

Replies

Best
Evaluated deepchecks shortly after launch. A ton of useful checks on models and data, some are easy to implement, some less so, but the real value IMHO is having a lot of these easily packaged. You can try checks you wouldn't have otherwise prioritiesed and only look deeper if they find an issue. Note however the AGPL license and verify if you can use free version or need some commercial agreement.
thanks, and glad you see the value in the package, and like the way, it is built! Licensing is always a complex issue, in our case we were looking for a solution that would enable free and open usage for any ML practitioner that's building their own model, but that would still enable us to avoid cases like the Elastic/Amazon licensing case. Based on numerous user interviews, I've learned that many of the concerns that are usually relevant to AGPL licenses don't apply to this case, since Deepchecks isn't used in the actual production code, but is only used to test the data/models before they are productionized. In any case, we'd love to collaborate on a business level with companies that are building ML platforms, and of course, this would include a designated license. On a different note, if there are any teams working on an interesting use case that are in need of a different license, please reach out, and let's see if we can find a solution.
Wonderful. I'm excited to try this out!
Thank you so much, we'd love to hear your feedback once you have it!
Helpful! congratulations on the launch!
thank you so much! And would love to hear your feedback once you have some...
Great tool and kick off. Would this be relevant for the use case of real time monitoring of autonomous vehicles?
Hi , and thanks for the positive feedback! This is definitely a relevant use case. As you may have seen, the Computer Vision module of Deepchecks is still in Beta. However, even the existing features would provide some important value for a this real time AV use case. There is still a hardware/runtime complexity issue that need some careful thought, but we’ve had discussions about this use case with relevant AV teams in the past. If you have a specific use case in mind - let’s discuss!
It seems to me that for a quick check and building an MVP is an awesome solution
Would be happy to hear your usage scenarios and any additional suggestions! Link for opening new issues: (⭐️ to support)
Congratulations on your launch! Good luck!
thanks! Much appreciated...
The testing package looks very comprehensive, and I see it achieved 1.8K GitHub stars in no time! Well done.
thanks! And I can't tell you how much we appreciate the support we've been receiving from the community
Congratulations on the product launch and the team! 🤩 Would love to give it a shot.
Happy to hear, looking forward for your feedback!!
Nailed it, fantastic!
Thanks! We've seen various use cases in academic areas, we would be happy to collaborate! (feel free to reach out via linkedin or in our community 🤓)
Excited to support this. Well done guys!
thanks, you rock!