added batchSize override to predict #27
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
--batchSizeOverride
toReLERNN_PREDICT
for those running out of memory when trying to stuff the genotype matrices for an entire chromosome into GPU memory.The default behavior is to generate a prediction batch with
batch_size
equal to the number of windows along a chromosome. If this creates an OOM error, the user can choose to set--batchSizeOverride
to a number < the number of windows along the chromosome, which will reduce memory consumption.Added a callback to terminate training upon
loss = NaN
Added ability to set a global seed to reduce non-deterministic behavior outside of training (model fitting is still non-deterministic).