You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/09/01 09:14:20 UTC

[GitHub] [tvm] mbrookhart commented on a change in pull request #8883: [Relay][Quantization] Per-Channel FQ2I

mbrookhart commented on a change in pull request #8883:
URL: https://github.com/apache/tvm/pull/8883#discussion_r699447863



##########
File path: python/tvm/relay/frontend/onnx.py
##########
@@ -478,7 +478,7 @@ def _impl_v1(cls, inputs, attr, params):
                 attr["dilations"] = [1] + list(attr["dilations"])
             if "pads" in attr:
                 attr["pads"] = [0, attr["pads"][0], 0, attr["pads"][1]]
-
+        attr["channels"] = kernel_shapes[0][0]

Review comment:
       This is a side fix, I utilized it for an intermediate solution for conv, but I guess I don't technically need it. It doesn't seem to be required in many of the relay passes.




-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org