-
Notifications
You must be signed in to change notification settings - Fork 129
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
Neuralsde #166
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM overall.
Let's get some basic correctness tests in for sdeint
before moving on to adaptive integration.
Codecov ReportAttention:
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## master #166 +/- ##
==========================================
+ Coverage 64.59% 66.15% +1.55%
==========================================
Files 27 29 +2
Lines 1881 2074 +193
==========================================
+ Hits 1215 1372 +157
- Misses 666 702 +36 ☔ View full report in Codecov by Sentry. |
This PR is ready to be merged. |
Opening the first PR for
NeuralSDE
for integrating sdeint into torchdyn. Also, as I formatted code files I have made changes using black, we can use this format for future uses if everyone likes it.The goal is to substitute sdeint module from
torchsde
into torchdyn native version. Will open different PRs for Brownian Interval and adjoint methods(+ other methods if possible).sdeint
with fixed step sizeNeuralSDE
module able to run trainingSDEFunc
module forNeuralSDE