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

add dynamic export and visualize to pytorch2onnx #463

Merged
merged 9 commits into from
Apr 12, 2021

Conversation

grimoire
Copy link
Member

@grimoire grimoire commented Apr 9, 2021

Hi
This PR adds dynamic export and visualize of pytorch2onnx.
Tested on FCN, PSPNet, DeeplabV3, DeeplabV3+.
Note that dynamic shape support of PSPNet is not fully supported cause ONNX does not support dynamic export of AdaptiveAvgPool.

@CLAassistant
Copy link

CLAassistant commented Apr 9, 2021

CLA assistant check
All committers have signed the CLA.

mmseg/ops/wrappers.py Outdated Show resolved Hide resolved
@xvjiarui
Copy link
Collaborator

xvjiarui commented Apr 9, 2021

We may also add usage here

@codecov
Copy link

codecov bot commented Apr 9, 2021

Codecov Report

Merging #463 (3152b42) into master (b9f9cf6) will decrease coverage by 0.01%.
The diff coverage is 37.50%.

❗ Current head 3152b42 differs from pull request most recent head 5ff17c7. Consider uploading reports for the commit 5ff17c7 to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##           master     #463      +/-   ##
==========================================
- Coverage   86.52%   86.50%   -0.02%     
==========================================
  Files          97       97              
  Lines        4964     4966       +2     
  Branches      807      806       -1     
==========================================
+ Hits         4295     4296       +1     
- Misses        515      517       +2     
+ Partials      154      153       -1     
Flag Coverage Δ
unittests 86.50% <37.50%> (-0.02%) ⬇️

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

Impacted Files Coverage Δ
mmseg/apis/inference.py 63.79% <0.00%> (-2.28%) ⬇️
mmseg/ops/wrappers.py 80.76% <ø> (-1.99%) ⬇️
mmseg/models/segmentors/encoder_decoder.py 90.84% <33.33%> (-1.16%) ⬇️
mmseg/models/losses/accuracy.py 100.00% <100.00%> (ø)
mmseg/version.py 58.33% <100.00%> (ø)
mmseg/datasets/pipelines/transforms.py 97.98% <0.00%> (+0.86%) ⬆️

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 b9f9cf6...5ff17c7. Read the comment docs.

tools/pytorch2onnx.py Outdated Show resolved Hide resolved
tools/pytorch2onnx.py Outdated Show resolved Hide resolved
@xvjiarui
Copy link
Collaborator

Hi @grimoire
Please kindly sign CLA.

@RunningLeon
Copy link
Collaborator

@xvjiarui done.

tools/pytorch2onnx.py Outdated Show resolved Hide resolved
docs/useful_tools.md Outdated Show resolved Hide resolved
docs/useful_tools.md Outdated Show resolved Hide resolved
RunningLeon and others added 2 commits April 12, 2021 11:07
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
@xvjiarui xvjiarui merged commit 789d1a1 into open-mmlab:master Apr 12, 2021
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
* add dynamic export and visualize to pytorch2onnx

* update document

* fix lint

* fix dynamic error and add visualization

* fix lint

* update docstring

* update doc

* Update help info for --show

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* fix lint

Co-authored-by: maningsheng <maningsheng@sensetime.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this pull request Dec 3, 2023
sibozhang pushed a commit to sibozhang/mmsegmentation that referenced this pull request Mar 22, 2024
* fix_merge_config

* pre-commit

* add changelog
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants