* reconstruct the run_sequence_labeling.py into train.py predict.py eval.py & add yalm configure

* reconstruct the ERNIE based LAC model

* Update train_ernie.py

recurrent multi-GPU nan

* update the ernie base model

* configure update

* update configure

* add inference model

* specification code

* delete unused run_sequence_labeling.py

* rename evaluate.py to compare.py

* add postfix '.pdckpt' to model

* update README.md

* add LAC class(for predict conveniently)

* add LAC class(for predict conveniently)

* update README.md

* fixed bug on run_ernie

* update default setting

* fix infenence bug in windows

* fix infenence bug in windows

* update new model and dateset

* delete the postfix .pdckpt of model checkpoint directory

* update new model's performance

* fixed the bug for empty input

* unusing of tqdm tools

* fix the bug of train_data

* update code for argparser

* add inference_model

* fix inference_model

* update create model for inference

* fix model nets conflict with Senta

* update readme

* fix_bug_server

* fix_readme

* update

* update

* update

* fix run_ernie.sh

* Update README.md

* MRQA2019-D-NET

* delete_data_file

* set encoding=utf8 for open

* set encoding=utf8 for open

add license for nlp models

Fix transformer inference when using ParallelExecutor by setting ExecutionStrategy to clear tensor array after each iteration. (#3374)

* minor fix

* add getting ops from program

* add obtaining op params from paddle program

* add code reusage of light_nas_space

* add comments to get_ops_from_program

* add comments to get_ops_from_program

* fixed bugs

* add get_all_ops

* add get_op_latency

* add platform parameter for get_op_latency

* add get_all_ops

* add get ops from shortcut and se

* bug fixed

* fixed bugs

* add refined code

* bugs fixed

* useless test codes and op files removed

* modifying 7 to length of searched bottlenecks

* bugs fixed

* add softmax op in get_ops_from_program

* remove resize ops in get_ops_from_program

* add get_op_latency from paddle-mobile and modify getting fc op params

* add fc op params

* add batch norm in light_nas_space

* bugs fixed

* update light_nas_space: add get_model_latency

* bug fixed

* bug fixed

* bug fixed

* update get_latency_lookup_table

* add bias of fc layer in get_all_ops

* add docs for light-nas with latency

* update doc for light-nas

* add first part of method descriptions for light-nas based on android and ios

* add descriptions for lightnas basd on android and ios in demo and usage and modify get_latency_lookup_table

* fix errors in usage.md

* fix errors among the contents of android system in usage.md

* fix errors among the contents of ios system in usage.md

* add descriptions in demo.md about lightnas based on android and ios

* add auxillary methods for generating bin files and .a files for op latency test

* add links for latency estimation tools

* minor fix in usage.md

* minor errors fixed in usage.md

* update LightNAS usage

* update docs

* update get_latency_lookup_table.

* add information for get latency lookup table

* add current searched models and their corresponding accuracies for android and ios systems

* bugs in fc_op_prams are fixed in get_ops_from_program.py test=develop

* update docs

* update docs

* update docs

* update PaddleSlim results

* add more lr_strategy

* update docs

* update PaddleSlim results

* update docs

* minor update

* minor update

* modify get_latency_lookup_table.py to make it compatible for python2 and python3; modify usage.md to update the information of PaddleMobile to Paddle-Lite

* minor update to be compatible for py3

* modify get_latency_lookup_table.py to make it compatible for python2 and python3

* convert float number in get_all_ops to int number in order to make it compatible for both python2 and python3

* remove print in get_latency_lookup_table.py

* update docs

* fixed bugs in get_all_ops

* fix merge conflicts

* fix merge conflicts

* move reading_comprehension into Research/ACL2018-DuReader

* move reading_comprehension into Research/ACL2018-DuReader

* move reading_comprehension into Research/ACL2018-DuReader

* move reading_comprehension into Research/ACL2018-DuReader

* move reading_comprehension into Research/ACL2018-DuReader

* fix the gru/gnn hang issue on windows with cuda10 test=develop

* add export cpu_nums for supporting cpu environment

* add export cpu_nums for supporting cpu environment

* Release auto mixed-precision training for bert

* Update README

* modify readme for not support windows cpu environment

* modify readme for python adaption

* add readme for KTNET

* update readme

* update readme

* update readme

* update readme of KTNET

* update readme of KTNET

* add source files for KTNET

* update files for KTNET

* update files for KTNET

* update draft of readme for KTNET

* modified scripts for KTNET

* fix typos in readme.md for KTNET

* update scripts for KTNET

* update scripts for KTNET

* update readme for KTNET

* edit two-staged training scripts for KTNET

* add details in the readme of KTNET

* fix typos in the readme of KTNET

* added eval scripts for KTNET

* rename folders for KTNET

* add copyright in the code and add links in readme for KTNET

* add the remaining download link for KTNET

* add md5sum for KTNET

* final version for KTNET

remove mem opt in PaddleNLP

This reverts commit 5e41760f.

* update .run_ce.sh

* chmod +x .run_ce.sh

* add elmo ce

* Refine the print and add timing for each step and epoch.

* Enable the profile.

Fix the data file empty check.
Fix the utf8 file encoding.
Refine the README.

remove knowledge-driven-dialogue from readme

* fix args bug and remove test code

* remove print code