New format quant model support for MKLDNN #45416
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jiangjiajun
reviewed
Aug 25, 2022
yghstill
previously approved these changes
Aug 29, 2022
…t_quant_model_dev
|
@yaomichael @yeliang2258 I can see there are only changes in C++ passes. Are you planning to add this ONNX format to python/paddle/fluid/contrib/slim/quantization/quant2_int8_mkldnn_pass.py that serializes models? |
|
@wozna According to the latest version, we only need to enable config.enable_mkldnn_int8(), no longer need to convert through save_quant_model.py script. So we no longer need to add codes to python/paddle/fluid/contrib/slim/quantization/quant2_int8_mkldnn_pass.py. |
wozna
reviewed
Aug 31, 2022
…t_quant_model_dev
wozna
previously approved these changes
Sep 2, 2022
yghstill
reviewed
Sep 2, 2022
sfraczek
reviewed
Sep 2, 2022
python/paddle/fluid/tests/unittests/mkldnn/test_onnx_format_quantization_mobilenetv1.py
Outdated
Show resolved
Hide resolved
leiqing1
previously approved these changes
Sep 5, 2022
qingqing01
reviewed
Sep 5, 2022
yeliang2258
dismissed stale reviews from leiqing1, wozna, and sfraczek
via
76ebfd9
XieYunshen
approved these changes
Sep 5, 2022
leiqing1
approved these changes
Sep 5, 2022
Caozhou1995
pushed a commit
to Caozhou1995/Paddle
that referenced
this pull request
Sep 9, 2022
* support onnx format quantized model * update code * add test * add test * fix * fix test * fix cmake * update code * change scale file path to calibration file path * update code * update code * fix build bug * fix build bugs * fix * fix
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
Others
Describe
New format quant model support for MKLDNN
CPU：Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz
Thread nums：1
Test model：https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression/pytorch_yolo_series
yolov5
yolov6
yolov7