zhiics commented on a change in pull request #4292: Retain qnn input kernel
scales
URL: https://github.com/apache/incubator-tvm/pull/4292#discussion_r345982936
##########
File path: python/tvm/relay/qnn/op/qnn.py
##########
@@ -219,6 +221,16 @@ def conv2d(data,
input_zero_point: int
The zero point of the data distribution.
+ input_scale: float
+ The scale for the input tensor. The scale for the input tensor is
+ stored purely for convenience here. See more commentary below.
+
+ kernel_scale: float
Review comment:
Move these two docstring below `kernel_zero_point` to keep consistent to the
order of the parameters.
----------------------------------------------------------------
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
