PyTorch vs TensorFlow | Ishan Misra and Lex Fridman

PyTorch has more applications over tensorflow

WHY THE FUCK IS LEX FRIDMAN TALKING ABOUT MACHINE LEARNING

Tensorflow...!
Great support, model integration and model deployment.

Pretty useless clip tbh, all he says is "I prefer Pytorch because I've been using it for longer". He mentions that the imperative style is easier to debug, but TensorFlow 2 also uses an imperative style.

TF usually has some features 1-2 year ahead pytorch. Pytorch is more flexible for tweaking the model. TF2.4-2.6 was very buggy with strange errors that took long time to fix. That was the time I switched to mainly pytorch. I think TF is better now.

More like collaboration than competition. The open source COMMUN-ity shows how a commune environment that shares resources can be so vastly superior to the capitalistic wealth redistribution scheme, it isn't even funny.

Both are great. TF with Keras has better performance, strong community support and robustness 👍PyTorch better for research and experimentation. Easier to use and debug since is more pythonic. Better Dynamic computation graph. Easier to deploy on web and mobile. Your choice will be determine on: use case and developer's preferences.

jax

I like calling pytorch imperative! Because it you would understand machine learning in better way! Unlike declarative approaches similar to Unix like command and SQL you give it a command or query and it would run. Even through that Tensorflow uses procedural language, coding with it similar to declaring command. And static graph structuring making it difficult especially for beginners debugging code!

wow 😀 ! you are diverse in your topics ! luv 'it 😘!

PyTorch is what I made a transition to from Tf2.x(x>=7). So far I see it quite cool & friendly to research community. And yes, I converted my entire TF code to PyTorch in less than 2weeks.

pytorch is more intuitive for SWEs, tensorflow is killer now with the keras integration

In college nobody told me to use Tensorflow for assignments and projects. It was Pytorch. Even Philip Koehn's lecture has Pytorch tutorial in it.

After keras integration tf is winner

doesn't answer the question at all :|

PyTorch’s source code is elegant and well thought out.

Asking a Facebook employee about pytorch vs tensorflow. 🤔

Pytorch Forever 🔥🔥🔥 ... I know the XLA TPU support isn't almost there yet but yeah Pytorch 🔥

Tensorflow is bread and butter

Interesting