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
Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.Sign up to join this community
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.