tmoreau89 commented on a change in pull request #4295: [Relay][Quantize]
Integrate data-aware calibration into quantization
URL: https://github.com/apache/incubator-tvm/pull/4295#discussion_r348163524
##########
File path: python/tvm/relay/quantize/quantize.py
##########
@@ -143,9 +141,20 @@ def qconfig(**kwargs):
nbit_dict: dict of QAnnotateKind -> int
Number of bit for every kind of annotate field.
+ calibrate_mode: str
+ The calibration mode. 'global_scale' or 'kl'.
Review comment:
can we spell it out so it's more self explanatory (e.g. `kullback_leibler`)?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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
