-
-
Notifications
You must be signed in to change notification settings - Fork 597
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Call of Flux.stack results in StackOverfloxError for approx. 6000 sequence elements of a model output of a LSTM #1585
Comments
What is the length it doesn't occur with? Could you post the complete stacktrace? |
Between a length of 5000 and 6000.
|
Interesting, this seems to be happening in Base. |
I've encountered this error before when splatting inside |
Looks like the limit on number of splattable arguments is known: JuliaLang/julia#30796 (comment) |
Well that confirms its a Base thing. |
Well a Base thing that is not going to be addressed. So we still need to update our code so that we don't hit the error. |
I may have discovered an error. When I simulate the trained model with a test data set longer than 10000 data points, I get a StackOverflowError due to the Flux.stack function
https://discourse.julialang.org/t/how-to-arrange-data-for-time-series-forecasting-mini-batching-without-violoating-the-gpu-memory-for-a-lstm/54171/8
it doesn’t occur with
Used versions of Julia and Flux:
Julia 1.6.0
Flux v0.12.2
The text was updated successfully, but these errors were encountered: