u99127 commented on a change in pull request #4629: [QNN] Channel wise
quantization - Quantize & Requantize
URL: https://github.com/apache/incubator-tvm/pull/4629#discussion_r364400908
##########
File path: include/tvm/relay/qnn/attrs.h
##########
@@ -33,10 +33,15 @@ namespace qnn {
/*! \brief Attribute for requantize operator */
struct RequantizeAttrs : public tvm::AttrsNode<RequantizeAttrs> {
+ int axis;
std::string rounding;
DataType out_dtype;
TVM_DECLARE_ATTRS(RequantizeAttrs, "relay.attrs.RequantizeAttrs") {
+ TVM_ATTR_FIELD(axis)
+ .describe("The output channel axis for channel wise quantization.
Default value is -1,"
+ "which corresponds to the last axis.")
Review comment:
I don't have an opinion on whether this is the right approach or not but the
question that popped in my mind was :
Why not be more explicit and say that axis == -1 actually means per-tensor
quantization ?
Thanks,
Ramana
----------------------------------------------------------------
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
