jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r191752075
##########
File path: ci/docker/runtime_functions.sh
##########
@@ -381,13 +381,12 @@ unittest_ubuntu_python3_cpu() {
unittest_ubuntu_python3_cpu_mkldnn() {
set -ex
- export PYTHONPATH=./python/
+ export PYTHONPATH=./python/
# MXNET_MKLDNN_DEBUG is buggy and produces false positives
# https://github.com/apache/incubator-mxnet/issues/10026
#export MXNET_MKLDNN_DEBUG=1 # Ignored if not present
export MXNET_STORAGE_FALLBACK_LOG_VERBOSE=0
nosetests-3.4 --verbose tests/python/unittest
- nosetests-3.4 --verbose tests/python/quantization
Review comment:
One note for removing "nosetests-3.4 --verbose tests/python/quantization"
for unittest_ubuntu_python3_cpu_mkldnn: this is due to we used
tests/python/mkl/test_quantization_mkldnn.py (will be tested when running
"nosetests-3.4 --verbose tests/python/mkl") to test mkldnn quantization so
could remove tests/python/quantization path.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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
