Комментарии:
PyTorch has more applications over tensorflow
ОтветитьWHY THE FUCK IS LEX FRIDMAN TALKING ABOUT MACHINE LEARNING
ОтветитьTensorflow...!
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.
ОтветитьTF 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.
ОтветитьMore 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.
ОтветитьBoth 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.
Ответитьjax
ОтветитьI 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!
Ответитьwow 😀 ! you are diverse in your topics ! luv 'it 😘!
ОтветитьPyTorch 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.
Ответитьpytorch is more intuitive for SWEs, tensorflow is killer now with the keras integration
ОтветитьIn college nobody told me to use Tensorflow for assignments and projects. It was Pytorch. Even Philip Koehn's lecture has Pytorch tutorial in it.
ОтветитьAfter keras integration tf is winner
Ответитьdoesn't answer the question at all :|
ОтветитьPyTorch’s source code is elegant and well thought out.
ОтветитьAsking a Facebook employee about pytorch vs tensorflow. 🤔
ОтветитьPytorch Forever 🔥🔥🔥 ... I know the XLA TPU support isn't almost there yet but yeah Pytorch 🔥
ОтветитьTensorflow is bread and butter
ОтветитьInteresting
Ответить