The State of Machine Learning Frameworks in 2019

Unless you’re working at Google, then maybe you use JAX.

In my experience, a lot of it comes down to the community and the ease of use. Debugging in PyTorch feels way more intuitive, and I wonder if that’s why so many people are gravitating toward it. I’ve seen countless tutorials and workshops pop up for PyTorch compared to TensorFlow recently, which speaks volumes to how quickly things can change.

But then again, TensorFlow's got its enterprise backing, and I can't help but think about the implications of that. How long can PyTorch ride this wave before it runs into pressure from industry demands? And as we look toward 2025, do you think we'll see a third contender emerge, or will it continue to be this two-horse race?

I think the only thing that could have saved TensorFlow at that point would have been some sort of enormous performance boost that would only work with their computation model. I'm assuming Google's plan was make it easy to run the same TensorFlow code on GPUs and TPUs, and then swoop in with TPUs that massively outperformed GPUs (at least on a performance per dollar basis). But that never really happened.

But the exciting new research is moving beyond the narrow task of segmentation. It's not just about having new models that get better scores but building larger multimodal systems, broader task definitions etc.

I think people have continued to work on it. There’s no single lab or developer, it mostly appears that the metrics for comparison are usually focused on the speed/MAP plane.

One nice thing is that even with modest hardware, it’s low enough latency to process video in real time.