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.

Sign up for GitHub

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

Jump to bottom

Quantization Aware Training #359

Closed
aa12356jm opened this issue Dec 17, 2020 · 1 comment
Closed

Quantization Aware Training #359

aa12356jm opened this issue Dec 17, 2020 · 1 comment

Comments

@aa12356jm
Copy link

expecting to be able to add quantization aware training for models, int8 models will greatly improve inference speed, thanks
@innerlee
Copy link
Contributor

Thanks for the suggestion. Quantization is a great feature, please make the request here #9 to help us prioritize. Thanks!

@aa12356jm aa12356jm mentioned this issue Dec 18, 2020
Open
rollingman1 pushed a commit to rollingman1/mmpose that referenced this issue Nov 5, 2021
@irvingzhang0512
[Improvement] Update docs about test crops. (open-mmlab#359)
47b1ca9 
* [Docs] Update docs about test crops.
1. Add more docs.
2. Update default configs in TSM model when using DenseSampleFrames.

* [Docs] Update docs about test crops
1. Add more docs.
2. Update default configs in TSM model when using DenseSampleFrames.

* calculate num_crops automatically

* remove `twice_sample/test_crops` in test_cfg

* update all tsm model `test_cfg['average_clips']` default value to 'prob'

* add changelog

* fix a bug when using tsn and `test_cfg['average_clips']='prob'`

* fix docs and add docs for open-mmlab#363

* use `num_segments` instead of `num_segs` in average_clip

* use `num_segs` in TSMHead and average_clip.
HAOCHENYE added a commit to HAOCHENYE/mmpose that referenced this issue Jun 27, 2023
@HAOCHENYE
[Refactor] Refactor data flow to make the interface more natural (ope…
8770c6c 
…n-mmlab#468)

* [Refactor]: modify interface of Visualizer.add_datasample (open-mmlab#365)

* [Refactor] Refactor data flow: refine `data_preprocessor`. (open-mmlab#359)

* refine data_preprocessor

* remove unused BATCH_DATA alias

* Fix type hints

* rename move_data to cast_data

* [Refactor] Refactor data flow: collate data in `collate_fn` of `DataLoader`  (open-mmlab#323)

* acollate data in dataloader

* fix docstring

* refine comment

* fix as comment

* refactor default collate and psedo collate

* foramt test file

* fix docstring

* fix as comment

* rename elem to data_item

* minor fix

* fix as comment

* [Refactor] Refactor data flow: `data_batch` argument of `Evaluator.process is a `dict` (open-mmlab#360)

* refine evaluator and metric

* compatible with new default collate

* replace default collate with pseudo

* Handle data_batch in metric

* fix unit test

* fix unit test

* fix unit test

* minor refine

* make data_batch optional

make data_batch optional

* rename outputs to predictions

* fix ut

* rename predictions to outputs

* fix docstring

* fix docstring

* fix unit test

* make outputs and data_batch to kwargs

* fix unit test

* keep signature of metric

* fix ut

* rename pred_sample arguments to data_sample(Visualizer)

* fix loop and ut

* [refactor]: Refactor model dataflow (open-mmlab#398)

* [Refactor] Refactor data flow: refine `data_preprocessor`. (open-mmlab#359)

* refine data_preprocessor

* remove unused BATCH_DATA alias

* Fix type hints

* rename move_data to cast_data

* refactor model data flow

tmp_commt

tmp commit

* make val_cfg and test_cfg optional

* roll back runner

* pass test mmdet

* fix as comment

fix as comment

fix ci in DataPreprocessor

* fix ut

* fix ut

* fix rebase main

* [Fix]: Fix test val ddp (open-mmlab#462)

* [Fix] Fix docstring and type hint of data flow (open-mmlab#463)

* Fix docstring of data flow

* change signature of hook

* fix unit test

* resolve conflicts

* fix lint
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@aa12356jm @innerlee