When I set out to write the 2nd edition of Deep Learning with Python, I thought it would be roughly the same length, and about 50% new content. Now that the draft is done: it's almost 2x longer and it's ~75% new content. Overall it's a lot more in-depth than the first edition.
-
Great Job ! Will it include distributed training ? I switched back from Pytorch to TF2/keras after finding out how effective, simple and fast it is with distributed training, particularly on TPU. But I still struggle with gradient accumulation in this context ^^
-
-
Does it cover deep reinforcement learning? Really looking forward to it! Can’t wait to see the draft
-
a BIG missing part in the 1st edition imo
End of conversation
New conversation -
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.