Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pytorch2onnx which can be used for DIM and GCA model #105

Merged
merged 9 commits into from
Jul 21, 2020

Conversation

drcut
Copy link
Contributor

@drcut drcut commented Jul 16, 2020

This PR support exporting DIM and GCA into ONNX format and comparing the execution results between Pytorch and ONNX.
However, as there is some bug in ONNX runtime, the results between Pytorch and ONNX for DIM may be different

@codecov
Copy link

codecov bot commented Jul 16, 2020

Codecov Report

Merging #105 into master will increase coverage by 0.02%.
The diff coverage is 91.30%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #105      +/-   ##
==========================================
+ Coverage   82.43%   82.45%   +0.02%     
==========================================
  Files         143      143              
  Lines        6591     6610      +19     
  Branches      980      980              
==========================================
+ Hits         5433     5450      +17     
- Misses       1060     1062       +2     
  Partials       98       98              
Flag Coverage Δ
#unittests 82.45% <91.30%> (+0.02%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmedit/models/common/gca_module.py 96.39% <ø> (ø)
...ckbones/encoder_decoders/decoders/plain_decoder.py 96.61% <90.00%> (-3.39%) ⬇️
mmedit/models/mattors/dim.py 79.59% <100.00%> (ø)
mmedit/models/mattors/gca.py 93.10% <100.00%> (ø)

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 68b7d60...0d65e88. Read the comment docs.

mmedit/models/common/gca_module.py Outdated Show resolved Hide resolved
mmedit/models/mattors/base_mattor.py Outdated Show resolved Hide resolved
mmedit/models/mattors/dim.py Show resolved Hide resolved
mmedit/models/mattors/gca.py Outdated Show resolved Hide resolved
tools/pytorch2onnx.py Outdated Show resolved Hide resolved
@hejm37 hejm37 merged commit df88b3f into open-mmlab:master Jul 21, 2020
wchstrife pushed a commit to wchstrife/mmediting that referenced this pull request Dec 26, 2020
* add pytorch2onnx for DIM

* support convert to ONNX for GCA

* use forward_dummy for onnx export

* remove useless comment

* retrieve useless modify

* Updating according to the latest mmcv

* modify the comment

* add docstring

* Fix docstring dot

Co-authored-by: Jiamin <1052020748@qq.com>
Yshuo-Li pushed a commit to Yshuo-Li/mmediting that referenced this pull request Jul 15, 2022
* add pytorch2onnx for DIM

* support convert to ONNX for GCA

* use forward_dummy for onnx export

* remove useless comment

* retrieve useless modify

* Updating according to the latest mmcv

* modify the comment

* add docstring

* Fix docstring dot

Co-authored-by: Jiamin <1052020748@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants