High level of compatibility

What are the best aspects of this product?

I appreciate how production levels can be optimized by this tool, thanks to how compatible it is with other frameworks. This tool also integrates deep learning models that are already optimized, and you can build machine learning models on top of that.

What aspects are problematic or could work better?

If you're working with mobile applications and only have limited space, you might find it harder to deploy models and therefore get slower executions. It's also device-dependent when it comes to module division.

What specific problems in your company were solved by this product?

Before publishing our research, we used this tool for image categorization of randomized data as well as for image classification. We then used that to compare with different libraries' performance. It's been a really big help in that regard.

Are you a current user of this product?

No