[GitHub] [incubator-mxnet] ChaiBapchya edited a comment on issue #16599: Imagenet inference to nightly fix

[GitBox <gi...@apache.org>]

ChaiBapchya edited a comment on issue #16599: Imagenet inference to nightly fix
URL: https://github.com/apache/incubator-mxnet/pull/16599#issuecomment-546154309
 
 
   > That's output from the test. Can you make sure that this test case is not skipped
   
   @marcoabreu MKLDNN passes!
   
   ```
   + ls -a ../../../lib
   
   ++ grep -oE mkldnn
   
   ++ tail -1
   
   + lib_name=mkldnn
   
   + [[ -n mkldnn ]]
   
   + [[ mkldnn =~ mkldnn ]]
   
   >>> INFO: INT8 dummy data
   
   + echo '>>> INFO: INT8 dummy data'
   
   + LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:../../../lib
   
   + ./imagenet_inference --symbol_file ./model/resnet50_v1_int8-symbol.json --batch_size 1 --num_inference_batches 500 --benchmark
   
   [23:12:52] cpp-package/example/inference/imagenet_inference.cpp:302: Loading the model from ./model/resnet50_v1_int8-symbol.json
   
   
   [23:12:52] src/executor/graph_executor.cc:2014: Subgraph backend MKLDNN is activated.
   
   [23:12:52] cpp-package/example/inference/imagenet_inference.cpp:424: Running the forward pass on model to evaluate the performance..
   
   [23:13:09] cpp-package/example/inference/imagenet_inference.cpp:439:  benchmark completed!
   
   [23:13:09] cpp-package/example/inference/imagenet_inference.cpp:440:  batch size: 1 num batch: 500 throughput: 29.8719 imgs/s latency:33.4763 ms
   
   ```
   
   Here - http://jenkins.mxnet-ci-dev.amazon-ml.com/blue/organizations/jenkins/NightlyTestsForBinaries/detail/shared_library_nightly_fix/7/pipeline/72

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services