* add PP-OCRv4_rec ultra config

* modify prepare

* fix set bug

* refine 960 to 640

* fix details

* add epoch num

* add rep export

* use db head

* fix gris_sample data type bug when use fp16

* fix gris_sample data type bug when use fp16

* fix v4rec batchsize

* fix bug of hang when multi gpus training(sampler)

* support min_area_rect crop

* add check_install

* fix requirement.txt

* fix check_install

* add lanms-neo for drrg

* fix

* fix doc

* fix

* support set gpu_id when inference

* fix #8855

* fix #8855

* opt slim doc

* fix doc bug

* add v4_rec_distill config

* delete debug

* fix comment

* fix comment

* add dml nrtr distill loss

* support min_area_rect crop

* add check_install

* fix requirement.txt

* fix check_install

* add lanms-neo for drrg

* fix

* fix doc

* fix

* support set gpu_id when inference

* fix #8855

* fix #8855

* opt slim doc

* fix doc bug

* add v4_rec_distill config

* delete debug

* fix comment

* fix comment

* fix gris_sample data type bug when use fp16

* fix gris_sample data type bug when use fp16

* fix v4rec batchsize

* support min_area_rect crop

* add check_install

* fix requirement.txt

* fix check_install

* add lanms-neo for drrg

* fix

* fix doc

* fix

* support set gpu_id when inference

* fix #8855

* fix #8855

* opt slim doc

* fix doc bug

* rename

* rename

* update table_mv3 tipc config

* update slanet tipc config

* update num_workers of vi_layoutxlm_ser

* add ch_PP-OCRv4_mobile_rec

* add PP-OCRv4

* update slanet tipc config

* change python3.7 to python

* update vi_layoutxlm_ser config

* update slanet tipc config

* update v4 rec config

* revert eval mode

* update hgnet config

* update for multi scale

* update for multi scale

* update for multi scale

* rm notes

* add v4 det pretrain link

* update size to 960

* add ppocrv4 det student and teacher model

* update head and config, refine details

* refine config and head details

* refine config and head details

* refine details

* refine details

* remove application

* refine fpn

* fix bug

* update code

* fix bug

* align lcnet to rec

* align hgnet to rec

* refine make shrink

* remove theseus layer

Co-authored-by: WenmuZhou <572459439@qq.com>

* v4rec code

* v4rec add nrtrloss

* Add V4rec backbone file

* Add V4Rec config file.

* Fix V4rec reparameters when export_model

* convert lvnetv3

* fix codestyle

* fix infer_rec v4rec

* add v4rec hgnet

* add v4rec hgnet config

* add svtr_hgnet

* fix bugs in infer_rec and hgnet

* v4rec code

* v4rec add nrtrloss

* Add V4rec backbone file

* Add V4Rec config file.

* Fix V4rec reparameters when export_model

* convert lvnetv3

* fix codestyle

* fix infer_rec v4rec

* add finetune en doc & test=document_fix

* fix dead link & test=document_fix

* fix dead link & test=document_fix

* update check img

* fix det res dtype

* update args default type & test=document_fix

* fix numpy version

* support numpy1.24.0

* fix doc & test=document_fix

* update doc

* Fix padding value in rec model, and box sort in det model

* Add FastDeploy support to deploy PaddleOCR models.

* Improve readme

* improve readme

* improve readme

* improve code

* improve readme

* improve readme and format

* improve readme and format

* improve readme and format

* improve readme

* improve readme

* improve readme

* Fix padding value in rec model, and box sort in det model

* Add FastDeploy support to deploy PaddleOCR models.

* Improve readme

* improve readme

* improve readme

* improve code

* improve readme

* improve readme and format

* improve readme and format

* improve readme and format

* improve readme

* improve readme

* add d2s train for slanet and v3

* fix bug

* udpate tipc to_static

* update db

* remove_print

* update benchmark_train.sh

* update maybe_download_params

* add d2t train support of svtr

* Fix padding value in rec model, and box sort in det model

* Add FastDeploy support to deploy PaddleOCR models.

* Improve readme

* improve readme

* improve readme

* improve code

* improve readme

* support min_area_rect crop

* add check_install

* fix requirement.txt

* fix check_install

* add lanms-neo for drrg

* fix

* fix doc

* fix

* support set gpu_id when inference

* fix #8855

* fix #8855

* opt slim doc

* fix doc bug

* fix east postprocess

* keep same version of clang-format with paddle

* cp #9176

* Fix padding value in rec model, and box sort in det model

* Add FastDeploy support to deploy PaddleOCR models.

* Improve readme

* improve readme

* improve readme

* improve code

* add d2s train for slanet and v3

* fix bug

* udpate tipc to_static

* update db

* remove_print

* update benchmark_train.sh

* update maybe_download_params

* add d2s train for slanet and v3

* fix bug

* support min_area_rect crop

* add check_install

* fix requirement.txt

* fix check_install

* add lanms-neo for drrg

* fix

* fix doc

* fix

* support set gpu_id when inference

* fix #8855

* fix #8855

* opt slim doc

* fix doc bug

* fix east postprocess

* keep same version of clang-format with paddle

* Fix padding value in rec model, and box sort in det model

* Add FastDeploy support to deploy PaddleOCR models.

* Improve readme

* improve readme

* add finetune en doc & test=document_fix

* fix dead link & test=document_fix

* fix dead link & test=document_fix

* update check img

* fix det res dtype

* update args default type & test=document_fix

* fix numpy version

* support numpy1.24.0

* fix doc & test=document_fix

* Add custom detection and recognition model usage instructions in re

* update

* Add custom detection and recognition model usage instructions in re

* add db net for benchmark

* rename benckmark to PaddleOCR_benchmark

* add addict to req

* rename

* add table master benckmark

* support tablemaster d2s train

* change num worker to 16

* adjust num_worker ser_layoutlm_xfund_zh.yml for better performance