I was watching this video and Sentdex mentioned he had to switch around 1024 by 3 model. What does he mean by 1024 by 3 model and what did he change around?

Edited: Youtube link with the timestamp where he talks about this topic

  • 2
    $\begingroup$ When does he say that? Don't make us watch a 17 minute video. $\endgroup$ – Emre May 8 '18 at 1:17
  • $\begingroup$ Add the timestamp link directly or the captions at that frame $\endgroup$ – Aditya May 8 '18 at 1:21
  • $\begingroup$ Sorry guys I was working. It's around at @3:30 $\endgroup$ – Jason Marsh May 8 '18 at 1:36
  • $\begingroup$ Can you please remove the downvote? I've added the video timestamp $\endgroup$ – Jason Marsh May 8 '18 at 1:44

At 3:30 in video, he mentions this switching. What he is referring to by 'switch around' is that he is specifying the size of the LSTM being used. The 1024 refers to number of cells (or size) of the LSTM, and the 3 is the number of layers.

In the tutorial page being referenced I the snippet he is referencing is:

python translate.py
  --data_dir [your_data_directory] --train_dir [checkpoints_directory]
  --size=256 --num_layers=2 --steps_per_checkpoint=50

For details on why LSTMs are useful for this task, check out the paper.

| improve this answer | |
  • $\begingroup$ no problem, and welcome to the site. cheers. $\endgroup$ – Pavel Savine May 8 '18 at 1:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.