delete the cuda8.0 links in cn and en doc except trt related and add more info about how to use capi, test=develop (#1557)

Update download link of inference lib package on windows.

* fix the DOC of Windows compile , install and inference lib

* fix inference lib package on windows

test=develop

test=develop

* add C-API inference document and provide demo in the doc

* add C-API inference document and provide demo in the doc

Fix the DOC of Windows compile , install and inference lib.

The cmake command for the Windows build installation should be modified.
Support download link for inference library of cuda10, update 1.5.2 download link for inference library.

* imporve windows inference lib doc

* update sample images for c runtime library part of english version

* refine build and install tutorial doc for paddle inference

* remove trt_benchamrk after merge it to trt doc

* refine trt doc, test=develop, test=document_preview

* add note for adding virtual destructor for nvinfer.h, add step 1 to get infer lib with trt, test=develop, test=document_preview

Python Inference API Documentation refining and updating based on PR #19353

The building and installing documentation should be updated because that the code of inference lib has changed. The current bug is that most of files under the inference library path are missed.

* add 1.5.1 inference lib download path for windows

* re-organize the doc format

* add lite

* lite clean

* update

* up

* update

* refine lite mobile doc (#962)

* update

* update

* update mobile according to paddle-mobile repo

* Update mobile_readme_en.md

* update paddle-mobile doc

* delete untracked file

* refine inference api

test=develop

* fix typo

* fix typo

* fix comments

* fix typo

* refine inference api

test=develop

* fix typo

* fix typo

* fix comments

* TRT预测库仅支持GPU编译

DLTP-739 完善tensorRT使用文档 TRT需要GPU编译

* DLTP-965 预测模型的保存和加载文档优化

* Windows_installation_English

* DLTP-1417 受训改为训练

* add python inference api doc

* fix typo

* Update native_infer.md

* Update paddle_tensorrt_infer_en.md

* Update paddle_tensorrt_infer_en.md

* Update doc/fluid/advanced_usage/deploy/inference/paddle_tensorrt_infer_en.md
Co-Authored-By: Nacosta123 <42226556+acosta123@users.noreply.github.com>

* Update paddle_tensorrt_infer_en.md

* Update paddle_tensorrt_infer_en.md

* hotfix deadlink (#811)

* Update native_infer_en.md (#787)

* Update install_Windows_en.md (#790)

* Update install_Windows_en.md

* Update install_Windows_en.md

* Update cluster_howto_en.rst (#791)

* Update cluster_howto_en.rst

* Update cluster_howto_en.rst

* Update doc/fluid/user_guides/howto/training/cluster_howto_en.rst
Co-Authored-By: Nacosta123 <42226556+acosta123@users.noreply.github.com>

* Update doc/fluid/user_guides/howto/training/cluster_howto_en.rst
Co-Authored-By: Nacosta123 <42226556+acosta123@users.noreply.github.com>

* Update cluster_howto_en.rst

* Update index_cn.rst (#813)

* Update native_infer_en.md

* Update native_infer_en.md

* recheck_structure&fix_typo

* fix_structure

* adjust_dist_structure

* fix_deadlink

* fix deadlink

* synchronize with develop (#642)

* update_commitid1.3 (#641)

* update inference c++ API doc (#634)

* update inference c++ API doc

* fix link

* thorough clean for doc (#644)

* thorough clean

* delete_DS_Store

* Cherrypick1.3 (#652)

* thorough clean

* delete_DS_Store

* [Don't merge now]update_install_doc (#643)

* update_install_doc

* follow_comments

* add maxdepth (#646)

* upload_md (#649)

* update_version (#650)

* Translation of 16 new apis (#651)

* fix_windows

* Final update 1.3 (#653)

* thorough clean

* delete_DS_Store

* update_1.3

* Deadlink fix (#654)

* fix_deadlinks

* update_docker

* Update release_note.rst

* Update index_cn.rst

* update_Paddle (#658)

* fix pic (#659)

* [to 1.3] cn api debug (#655) (#661)

* debug

* fix 2 -conv2d

* "锚" ==> anchor(s)