[onnx] classification models export #830

felixdittrich92 · 2022-02-22T14:38:56Z

Counterpart of #789 for all classifiaction models

onnx export integrated in classification training script
classification models onnx export test

Issue:
#789

Any feedback is welcome 🤗

codecov · 2022-02-22T14:46:06Z

Codecov Report

Merging #830 (6976419) into main (7f396ca) will increase coverage by 0.00%.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##             main     #830   +/-   ##
=======================================
  Coverage   94.84%   94.85%           
=======================================
  Files         133      133           
  Lines        5200     5204    +4     
=======================================
+ Hits         4932     4936    +4     
  Misses        268      268

Flag	Coverage Δ
unittests	`94.85% <100.00%> (+<0.01%)`	⬆️

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

Impacted Files	Coverage Δ
doctr/models/utils/pytorch.py	`100.00% <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 7f396ca...6976419. Read the comment docs.

* feat: Added new resnets * feat: Added ResNet101 * fix: Fixed ResNet31 & ResNet34 wide * feat: Added new pretrained resnets * style: Fixed isort * fix: Fixed ResNet architectures * refactor: Refactored LinkNet * feat: Added more LinkNets * fix: Fixed MAGResNet * docs: Updated documentation * refactor: Removed ResNet101 * fix: Fixed warning * fix: Fixed a few bugs * test: Updated unittests * docs: Fixed docstrings

* feat: replace bce by focal loss in linknet loss * fix: requested changes * fix: mask reduction * fix: mask reduction * fix: loss reduction * fix: final adjustements * fix: final changes

This reverts commit 6511183.

This reverts commit 72e5e0d.

felixdittrich92 · 2022-03-11T23:16:04Z

@fg-mindee
Any update ? Or keep it for review after 0.5.1 release ? 😄

charlesmindee

Thanks for this PR, I think the right place for the export_to_onnx() function might be in the package, in the models/utils/export.py file or something like that, what do you think ?

references/classification/train_pytorch.py

tests/pytorch/test_models_classification_pt.py

felixdittrich92 · 2022-04-04T12:40:27Z

@charlesmindee ok i have moved it to utils/pytorch ftm 👍 and also removed both deps we can use torch.onnx and the quantization maybe later add directtly as one line in the training scripts wdyt ?

charlesmindee

Thanks for this PR, it is better without the dep, just need to remove it from the setup file!

setup.py

charlesmindee

Thanks for this feature !

* backup * onnx classification * fix: Fixed some ResNet architecture imprecisions (mindee#828) * feat: Added new resnets * feat: Added ResNet101 * fix: Fixed ResNet31 & ResNet34 wide * feat: Added new pretrained resnets * style: Fixed isort * fix: Fixed ResNet architectures * refactor: Refactored LinkNet * feat: Added more LinkNets * fix: Fixed MAGResNet * docs: Updated documentation * refactor: Removed ResNet101 * fix: Fixed warning * fix: Fixed a few bugs * test: Updated unittests * docs: Fixed docstrings * update with new models * feat: replace bce by focal loss in linknet loss (mindee#824) * feat: replace bce by focal loss in linknet loss * fix: requested changes * fix: mask reduction * fix: mask reduction * fix: loss reduction * fix: final adjustements * fix: final changes * Revert "feat: replace bce by focal loss in linknet loss (mindee#824)" This reverts commit 6511183. * Revert "fix: Fixed some ResNet architecture imprecisions (mindee#828)" This reverts commit 72e5e0d. * happy codacy * sapply suggestions * fix-setup * remove onnx from test req * move onnx deps ftm to torch * up * up * revert requirements * fix * update docstring * up Co-authored-by: F-G Fernandez <[email protected]> Co-authored-by: Charles Gaillard <[email protected]>

felixdittrich92 added 8 commits January 11, 2022 08:34

backup

81c313e

Merge branch 'mindee:main' into main

50574b5

Merge branch 'mindee:main' into main

5a6ed54

Merge branch 'mindee:main' into main

b9958a7

Merge branch 'mindee:main' into main

14c4651

Merge branch 'mindee:main' into main

779731f

Merge branch 'mindee:main' into main

ce2cdda

onnx classification

76b9652

fg-mindee self-assigned this Feb 22, 2022

fg-mindee and others added 3 commits February 23, 2022 12:42

update with new models

1633679

feat: replace bce by focal loss in linknet loss (mindee#824)

6511183

* feat: replace bce by focal loss in linknet loss * fix: requested changes * fix: mask reduction * fix: mask reduction * fix: loss reduction * fix: final adjustements * fix: final changes

felixdittrich92 force-pushed the onnx-classification branch from 671f137 to 6511183 Compare February 24, 2022 07:41

felixdittrich92 added 3 commits February 24, 2022 08:42

Revert "feat: replace bce by focal loss in linknet loss (mindee#824)"

5e77167

This reverts commit 6511183.

Revert "fix: Fixed some ResNet architecture imprecisions (mindee#828)"

5c0a514

This reverts commit 72e5e0d.

happy codacy

21218aa

fg-mindee added module: models Related to doctr.models topic: onnx ONNX-related type: new feature New feature labels Mar 7, 2022

fg-mindee self-requested a review March 7, 2022 11:29

charlesmindee reviewed Apr 4, 2022

View reviewed changes

references/classification/train_pytorch.py Outdated Show resolved Hide resolved

tests/pytorch/test_models_classification_pt.py Outdated Show resolved Hide resolved

felixdittrich92 added 7 commits April 4, 2022 13:28

sapply suggestions

8ddb081

fix-setup

191aa20

Merge branch 'main' into onnx-classification

fe2bcbe

remove onnx from test req

d0b1efc

move onnx deps ftm to torch

be55545

up

b97512b

up

6b3971d

felixdittrich92 added 2 commits April 4, 2022 14:19

revert requirements

d31f626

fix

ee7a3c2

felixdittrich92 requested a review from charlesmindee April 4, 2022 12:38

felixdittrich92 added 2 commits April 4, 2022 19:33

update docstring

f52fa83

up

6976419

charlesmindee reviewed Apr 5, 2022

View reviewed changes

setup.py Show resolved Hide resolved

setup.py Show resolved Hide resolved

charlesmindee approved these changes Apr 5, 2022

View reviewed changes

charlesmindee merged commit 1b4b687 into mindee:main Apr 5, 2022

felixdittrich92 deleted the onnx-classification branch April 5, 2022 14:19

felixdittrich92 mentioned this pull request Jul 7, 2022

[models] Ensure all PyTorch models are ONNX exportable #789

Closed

10 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[onnx] classification models export #830

[onnx] classification models export #830

felixdittrich92 commented Feb 22, 2022 •

edited

Loading

codecov bot commented Feb 22, 2022 •

edited

Loading

felixdittrich92 commented Mar 11, 2022

charlesmindee left a comment

felixdittrich92 commented Apr 4, 2022

charlesmindee left a comment

charlesmindee left a comment

[onnx] classification models export #830

[onnx] classification models export #830

Conversation

felixdittrich92 commented Feb 22, 2022 • edited Loading

codecov bot commented Feb 22, 2022 • edited Loading

Codecov Report

felixdittrich92 commented Mar 11, 2022

charlesmindee left a comment

Choose a reason for hiding this comment

felixdittrich92 commented Apr 4, 2022

charlesmindee left a comment

Choose a reason for hiding this comment

charlesmindee left a comment

Choose a reason for hiding this comment

felixdittrich92 commented Feb 22, 2022 •

edited

Loading

codecov bot commented Feb 22, 2022 •

edited

Loading