Skip to content
This repository was archived by the owner on Nov 17, 2023. It is now read-only.

Conversation

@Kh4L
Copy link
Contributor

@Kh4L Kh4L commented May 6, 2020

Description

MXNet was previously failing when built with USE_TENSORRT=1:

src/operator/subgraph/tensorrt/nnvm_to_onnx.cc:34:10: fatal error: operator/nn/deconvolution-inl.h: No such file or directory
 #include <operator/nn/deconvolution-inl.h>

Change the include of nn/deconvolution-inl.h in src/operator/subgraph/tensorrt/nnvm_to_onnx.cc to a relative include.

MXNet now builds successfully with USE_TENSORRT=1.

Signed-off-by: Serge Panev <spanev@nvidia.com>
@mxnet-bot
Copy link

Hey @Kh4L , Thanks for submitting the PR
All tests are already queued to run once. If tests fail, you can trigger one or more tests again with the following commands:

  • To trigger all jobs: @mxnet-bot run ci [all]
  • To trigger specific jobs: @mxnet-bot run ci [job1, job2]

CI supported jobs: [unix-cpu, centos-gpu, sanity, centos-cpu, unix-gpu, windows-cpu, edge, miscellaneous, windows-gpu, website, clang]


Note:
Only following 3 categories can trigger CI :PR Author, MXNet Committer, Jenkins Admin.
All CI tests must pass before the PR can be merged.

@marcoabreu marcoabreu merged commit 21b187b into apache:master May 7, 2020
AntiZpvoh pushed a commit to AntiZpvoh/incubator-mxnet that referenced this pull request Jul 6, 2020
Signed-off-by: Serge Panev <spanev@nvidia.com>
@Kh4L Kh4L mentioned this pull request Jul 27, 2020
@szha szha added this to the v1.8.0 milestone Aug 23, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants