d-smirnov commented on a change in pull request #7251:
URL: https://github.com/apache/tvm/pull/7251#discussion_r559784450
##########
File path: tests/python/contrib/test_arm_compute_lib/test_dense.py
##########
@@ -101,7 +101,7 @@ def _get_qnn_model(
out = relay.qnn.op.requantize(
out,
relay.const(input_sc * kernel_sc, "float32"), # input scale
- relay.const(input_zp * kernel_zp, "int32"), # input zero point
+ relay.const(0, "int32"), # input zero point
Review comment:
Should be zero, as dense already counted all the input zero points in.
----------------------------------------------------------------
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]
