* fix some configs

* fix doc

* change PyReader to from_generator

* fluid.layers.data->fluid.data

* fix_bug

* user new save load in all dygraph modell; test=develop

* change load_dict to set_dict; test=develop

* add_multiprocess_train_to_image_classification

unify reader to dataloader

* update

* update

* Update README.md

* Update run.sh

* Update utils.py

* Document mixed precision training flags

* Clarify GPU is required for mixed precision training

* update

* update

* Update README.md

* Update run.sh

* refine build strategy for the model optimize test=develop

* fix according develop test=develop

* 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

* ini commit for deepvoice, add tensorboard to requirements

* fix urls for code we adapted from

* fix makedirs for python2, fix README

* fix open with encoding for python2 compatability

* fix python2's str(), use encode for unicode, and str() for int

* fix python2 encoding issue, add model architecture and project structure for README

* add model structure, add explanation for hyperparameter priority order.

* fix fc prefix name

* add CropImageWithDataAnchorSampling
* Refine bbox sampling code
* Update comments
* fix import and variable problem

* update code for argparser

* add inference_model

* fix inference_model

* update create model for inference

* fix model nets conflict with Senta

* update readme

* Add backbone and architecture for FaceBoxes and Blazeface.
* Add dataloader for WIDERFace dataset.

Update ppdet/utils/checkpoint.py to skip the var shape check when the var is not initialized. (#3452)

* fix resnet prefix

* fix data path