* fix fuse_reduce_op quantization bug test=develop

* close fuse_all_reduce_ops in PaddleSlim, test=develop

* Leave fake quantization around mul

* Replace Fake with Real Quantized Mul

* Gather all scales from fake_quantize_ops

* Enable uint8 in conv_relu tensors

* Disable int8 mul and restore fake mul

* Fix buf for running QAT on VGG16 and 19

* fix next_tokens of controller

* Follow Wangzhen's comment in PR 18970, test=develop

* Review comments, test=develop

* Leave fake quantization around mul

test=develop

* Replace Fake with Real Quantized Mul

test=develop

* Fix bug in quantize placement pass

Nodes in the graph now have checked type instead of node name when they are to be marked for quantization test=develop

* Make PaddleSlim support PyReader.
* Fix unittest of sensitive pruning.
* Add some assert.

* Add support for new QAT models

test=develop
Co-Authored-By: NMichał Gallus <michal.gallus@intel.com>
Co-Authored-By: NWojciech Uss <wojciech.uss@intel.com>

* fixed fps results

test=develop

* fix top5 accuracy drop problem

* updated for new QAT models

* skip quantizing average pooling - dirty but working

* add missing pass

* added missing conv+brelu fuse pass

* removed a call to non-existent pass

test=develop

* renamed pass

test=develop

* Adjust finding pooling scale to newest QAT models

* Remove unnecessary code from quantization_mkldnn_pass

* Copy Pooling input scale to output scale in QAT

* Refactor & remove unused code in QAT

* Incorporate fp32 FC into QAT

test=develop

* Enable graph drawing with debug flag

test=develop

* Add tests for QATv2

* Fix paths for QATv2 models

test=develop

* Add option to save transformed int8 qat model

test=develop

* Remove redundant lines from qat mkldnn pass

test=develop

* Delegate disablement of avg pooling to qat

test=develop

* fix CI bug, test=develop

* Follow Wangzhen's Review, test=develop

* Update API.spec

test=develop

* Name False in (is_unsigned, TensorScale) tuple

test=develop

1. Support customize eval function instead of eval program.
2. Fix loading checkpoint in quantization strategy.
3. Support saving eval model when saving a checkpoint.
4. Fix decoder of loading context in PaddleSlim.
5. Fix restoring from the checkpoint of uniform prune strategy.
6. Support saving eval model and infer model during training.
7. Add ‘unitest’ for saving eval model, saving infer model and uniform pruning restoring from the checkpoint.
8. Fix pruning of depthwise_conv_grad op by updating the groups.

* add fake_quant_dequant_op for average pool2d
* add test

* support_dispensable_student_loss, test=develop

* add distillation test, test=develop

* fix distillation test non convergence problem, test=develop

* fix test_distillation fail problem, test=develop

* split teacher checkpoints with student checkpoints, test=develop

* add unittest for graph.merge(), test=develop

* delete useless raw variables in Conv2D, test=develop

* adjust the vars number in test_graph_wrapper to pass unittest, test=develop

test=develop

test=develop

* fix bug of getting bool Flags from os.environ, test=develop

* add empty loss_name in CompiledProgram for inplace grad test, test=develop

* python inference api supports numpy and add unit test, fix unit test fail in test_slim_int8_googlenet and test_slim_int8_mobilenet

* update light_nas_strategy: add latency constraint

test=develop

* update light_nas_strategy: update get_model_latency

test=develop

* update light_nas_strategy: add more check

test=develop

* update light_nas test

test=develop

* update light_nas test

    test=develop

* minor update light_nas test

    test=develop

* minor update light_nas test

test=develop

* update light_nas test

test=develop

* update _constrain_func of light_nas_strategy

test=develop

* update _constrain_func of light_nas_strategy

test=develop

* remove unused code

test=develop

* add pool2d quantization support, only for max-pooling.

* add the partial quantization support.

* update exe.run

test=develop

test=develop

Socket can't be pickled.
test=develop

* Enable MKL-DNN for slim FP32 vs. INT8 tests

test=develop

* added test for MobileNetV1 with MKL-DNN

test=develop

* QAT doc first version

* follow the comments, test=develop

* update the benchmark, test=develop

* Change to channel-wise, test=develop

* fix spelling errors; test=develop

* Update API.spec

update md5

* Update API.spec

* change the order of api;test=develop

test=develop

* update CPU_NUM config
test=develop

* added unit test for QAT FP32 & INT8 comparison

test=develop

* enabled other models and updated filenames

test=develop

* added accuracy check and multiple batch handling

test=develop

* removed quantization_mkldnn_pass.py

test=develop

* cleanup

test=develop

* updated model paths

test=develop

* renamed tests without MKL-DNN

test=develop

* fix reusing mkldnn pool2d primitive

test=develop

* add performance measuring

test=develop

* fix accuracy statistics

test=develop

* removed non-mkldnn tests

test=develop

* added conv2d_depthwise->conv2d mkldnn transformation

test=develop

* format update

test=develop

* fixed creating key for pool2d grad

test=develop

* added pass

* Fix the accuracy issue while using float precision to get the scale.

test=develop

* Fix the format issue when 'X' is not nchw.

test=develop

* removed output comparing and changed number of images

test=develop

* cmake and comment fix

test=develop

* updated acc threshold for QAT comparison tests

test=develop

* added OMP_NUM_THREADS setting

test=develop

* enable all QAT INT8 tests

test=develop

* restored upstream version of a file

test=develop

* modified directory names

test=develop

* fix logging unable. test=develop

* unset sys.stdout for stream handler. test=develop

* fix newly add basicConfig. test=develop

* fix import error. test=develop

1. Enhence auto pruning. 
2. Fix save/load graph when using py_reader.
test=develop

* Add auto pruning strategy.
1. Fix compressor.
2. Enhence graph executor.
3. Add SAController
4. Add auto pruning strategy.
5. Add unitest for auto pruning strategy.
test=develop

* Init light-nas

* Add light nas.

* Some fix.
test=develop

* Fix sa controller.
test=develop

* Fix unitest of light nas.
test=develop

* Fix setup.py.in and API.spec.
test=develop

* Fix unitest.
1. Fix unitest on windows.
2. Fix package importing in tests directory.

* 1. Remove unused comments.
2. Expose eval_epoch option.
3. Remove unused function in search_agent.
4. Expose max_client_num to yaml file.
5. Move flops constraint to on_epoch_begin function
test=develop

* Fix light nas strategy.
test=develop

* Make controller server stable.
test=develop

* 1. Add try exception to compressor.
2. Remove unitest of light-nas for windows.
test=develop

* Add comments
Enhence controller
test=develop

* Fix comments.
test=develop

* refactor PR 16865

* delete mergetool files

* test=develop

* test=develop

* test=develop

* test=develop

* create dir for int8 model before call SaveOptimModel

* test=develop

* mkldnn int8 only support linux; test=develop

* refine code; test=develop

* remove comment; test=develop

* refine code; test=develop

* fix bug; test=develop

* add exception for mkldnn_post_training_strategy

* reuse int8v2 CAPI dataset; test=develop

* fix accuracy check bug; test=develop

* remove tab

* convert files to unix format

* test=develop

* reduce CI time;test=develop

* reduce CI time and refine code;test=develop

* refine comment; test=develop

* add cmake FLAGS;test=develop

* remove predict_num;test=develop

* add quant_dequant_pass, test=develop

* Add quant_dequant before some ops, such as the elementwise_add op. This is required by TensorRT. test=develop