What is ONNX?

Key Takeaways

[Music] hey there it's joseph from roboflow here with jacob ml engineer at roboflow and it's another ml minute so jacob what is onyx so onyx is an intermediary machine learning framework used to convert between different machine learning frameworks so let's say you're in tensorflow and you want to get to tensorrt or you're in pi torch and you want to get to tf lite or some other machine learning framework onyx is a really good intermediary to use to convert your model as you're going through these different machine learning frameworks so onyx has worked really hard to basically implement all kinds of different neural network functions and different functionalities in these machine learning models so it can support sort of this cross-functionality to have this sort of like baseline uh common framework to convert into any pitfalls when working with onyx yeah certainly i mean one thing is that you know as onyx builds they're building new functions into it and you know they're they're building now they're trying to keep track of all the new research that's being done in machine learning but you know these versions can fall behind and you can you know have one version of tensorflow which is not compatible with one version of onyx and you have to be kind of upgrading and downgrading these these versions to try to find a pathway through them all or maybe even editing your model awesome that's another ml minute don't forget to like and subscribe to see more videos like this and catch on the next one