"The war between ML frameworks has raged on since the rebirth of deep learning." That's a bit too dramatic though, no?https://twitter.com/gradientpub/status/1182327049307844613 …
-
FYI the actual split in the research world is ~30-40% PT vs ~60-70% TF/Keras. This is the range of numbers you get by looking at 1) ArXiv mentions data, 2) Colab usage, 3) Actual research surveys. All the sources I can think of end up in this range. Extremely dishonest article.
Academic research is also literally the only usage category where you will see high PyTorch numbers (above 30%). And it's a very narrow category (~5% of TF usage).
-
-
Do you have any proof for these claims? At least from
@cHHillee we know how the numbers were derived. Also, what are your responses to a) his ablation study to include Keras to TF (no significant increase) and b) that he tackles more than NLP?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Lmfao Francois, you're one big butt hurt dude
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.