aaronmarkham commented on a change in pull request #13165: Addressed doc issues
URL: https://github.com/apache/incubator-mxnet/pull/13165#discussion_r231699225
##########
File path: python/mxnet/optimizer/optimizer.py
##########
@@ -692,18 +692,18 @@ class LBSGD(Optimizer):
Parameters
----------
momentum : float, optional
- The momentum value.
- multi_precision: bool, optional
- Flag to control the internal precision of the optimizer.
- ``False`` results in using the same precision as the weights (default),
- ``True`` makes internal 32-bit copy of the weights and applies gradients
- in 32-bit precision even if actual weights used in the model
have lower precision.`<
- Turning this on can improve convergence and accuracy when
training with float16.
- warmup_strategy: string ('linear', 'power2', 'sqrt'. , 'lars' default :
'linear')
- warmup_epochs: unsigned, default: 5
- batch_scale: unsigned, default: 1 (same as batch size*numworkers)
- updates_per_epoch: updates_per_epoch (default: 32, Default might not
reflect true number batches per epoch. Used for warmup.)
- begin_epoch: unsigned, default 0, starting epoch.
+ The momentum value.
+ multi_precision : bool, optional
+ Flag to control the internal precision of the optimizer.
Review comment:
Please talk to @Roshrini and let her know what changes you suggest since
this [file is getting updated in her
PR](https://github.com/apache/incubator-mxnet/pull/13160/files)... might be
easier to have hers handle this file's update. Can you describe the need to add
the extra space after the parameter name and before the colon?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
