* add dygraph ptq and refine dygraph qat

* add unit test for ptq

* update according to comments

* Fix skipping leaves option
* Add unitests

* fix superbn

* update_check_ss

* update_check_ss

* update_check_ss

* ss_multi_output

* remove_some_comments

* Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSlim into update_check_ss

* merge_conflicts

* add_coverage

* new_export_func

* add_test

* remove_kernel_prune

* add_test_&_update_clear_ss

* fix key_error in pruner

* add unit test for get_ratios_by_loss

* add distill dirs

* fix unittest

* prune the optimizer in dygraph mode

* set opt when initializing pruner

* tests passed locally

* update Chinese docs and tutorials

* refine docs style

* avoid ambiguation in docs

* fix get sub model

* fix

* update

* update

* update include_self

* fix dist

* fix

* remove hook

* fix skip layers

* fix depthwise

* fix depthwise

* fix depthwise

* add gp_nas

* add_syncbn

* fix when kernel size is even

* fix name

* fix weight_op

* fix shortcut

* fix when kernel_size in ss

* fix export

* fix dp

* fix export model prune param twice

* add comment

* fix unittest

* fix

* update

Co-authored-by: Nceci3 <ceci3@users.noreply.github.com>

* add export model and depth

* Support for pruning training graph with auxiliary parameters

* Fix bugs

* Fix unitests.

* add ofa api docs

* fix when param name is not None

* fix

* fix when lambda is None

* for bert

* support 2.0

* fix dataloader

* fix bugs for ernie

* Added dygraph quantization.

* Added save_quant_model function

* Overload quant_aware, make dynamic and static model use the same interface.

* Use singledispatch to overload the quant aware for dygraph quantization

* Add unnitest for dygraph quant_aware

* Use 2.0 api for supporting paddle 2.0

* Using pre-commit to modify the coding style.

* Add unittest for user inputted quant_config.

* Add singledispath into requirements.txt
Co-authored-by: NBai Yifan <me@ethanbai.com>