* fix pruned model save and load, fix bugs of pruning depthwise conv

* add unit test of pruned model save and load

* temp delete

* add unit test

* add some unit tests

* complete autoprune unit test

* add sensitive unit tests

* fix some unit test

* fix auto_pruner.py

* fix pruned model save and load, fix bugs of pruning depthwise conv

* add unit test of pruned model save and load

* temp delete

* add unit test

* fix bug when prune the depthwise convolution layer

* fix bug when prune the depthwise convolution layer

* fix bug when prune depthwise convolution layer

* fix pruner when prune depthwise convolution layer

* remove print from unit test

* fix dml issue

* disable multiprocess reader

* add other model

* add dml unittest

* fix log_softmax

* make dml compatible with 1.8 and 2.0 version paddle

* fix coverage

* fix unittest error

* fix quant_post unittest error

* add out scale for quantization

* update quant_aware unittest

* update quant_aware unittest

* add darts unittest

* fix

* fix some trouble

* update

* add quant_post_only_weight

* update quant_post_weight

* change paddle version requirments

* add test for quant_post_only_weight

* Add group_param to collect relative covolution into groups.

* Support custom functions when computing pruned substructure of parameter
1. Support custom criterion of importance
2. Support custom importance sorting strategy

* add default config and support more ops

* remove debug code

* remove debug code

* fix details

* add slim pruning implementation and related unitest test=develop

2. Fix unittest of sa nas

2. Add copyright.
3. Rmove FLOPS from graph wrapper.