* update model save load

* first add

* update model save and load

* update train.py

* update LaneNet model saving and loading

* adapt slim to paddle-1.8

* update distillation save and load

* update nas model save and load

* update model load op

* update utils.py

* update load_model_utils.py

* update model saving and loading

* add_vdl

* Update docs for visualdl.

* modify label tool

* add lovasz loss

* lovasz

* model builder

* test

* lovasz

* update lovasz

* update lovasz

* add sh yaml

* add sh yaml

* add sh yaml

* no per_image and device_guard

* no per_image and device_guard

* Update lovasz_loss.md

* Update lovasz_loss.md

* Update lovasz_loss.md

* Update lovasz_loss.md

* Update lovasz_loss.md

* elementwise_mul replace matmul

* save inference model

* fix details

* add export model in quantization

* remove useless code

* remove useless code

* change fluid.layers.data to fluid.data

* add prune distill nas

* update readme

* update readme

* remove debug code

* update all docs involving color label

* modify usage.md

* usage.md

* Update data_prepare.md

* Update jingling2seg.md

* Update jingling2seg.md

* Update labelme2seg.md

* Update jingling2seg.md

* a

* Update config.md

* Update config.md

* Update config.py

* Update config.py

* Update config.py

* Update config.md

* Update basic_group.md

* Update basic_group.md

* Update data_aug.md

* Update config.md

* Update finetune_pspnet.md

* Update finetune_pspnet.md

* Update finetune_unet.md

* Update finetune_unet.md

* Update finetune_icnet.md

* Update finetune_pspnet.md

* Update finetune_hrnet.md

* Update README.md

* Update finetune_deeplabv3plus.md

* Update finetune_deeplabv3plus.md

* Update README.md

* Update config.md

* Update train_group.md

* Update models.md

* Update model_group.md

* Update model_group.md

* Update train_group.md

* Update train_group.md

* Update model_group.md

* Update model_group.md

* Update README.md

* Update README.md

* Update models.md

* Add files via upload

* Add files via upload

* Update models.md

* Update models.md

* update solver.py and model_builder.py

* add hrnet

* fp16_err

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* add fp16 and multiple gpus train

* update solver_group.md

* del reset_dataset

* add pspnet turtorial

* add model

* Update data_aug.md

* Update config.py