apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
2,372 Commits 29 Branches 10 Tags
f5bea8bf37fa9e43dca4da5a4e39e18047f04526
Commit Graph

2372 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
DefTruth
f5bea8bf37 [Bug Fix] fixed paddlex ppseg pp-trt infer error (#2049) 
* [benchmark] fixed paddlex benchmark for picodet 320

* [Bug Fix] fixed paddlex ppseg pp-trt infer error
 2023-06-20 23:24:31 +08:00
DefTruth
1144e0a484 [benchmark] fixed paddlex benchmark for picodet 320 (#2046) 2023-06-20 14:14:22 +08:00
Horror Proton
7191d2da20 [Backend] Remove deprecated ort api (#2034) 
* [Backend] Remove deprecated ort api

`Ort::CustomOpApi` deprecated in ONNXRuntime 1.15

fix https://github.com/PaddlePaddle/FastDeploy/issues/2033

* Improve compatibly with ort older than 1.14

* Update fastdeploy/runtime/backends/ort/ops/multiclass_nms.cc

Co-authored-by: Horror Proton <107091537+horror-proton@users.noreply.github.com>

* Fix double free and wrong attrib type in ort/ops

---------

Co-authored-by: Jason <928090362@qq.com>
 2023-06-15 21:35:58 +08:00
DefTruth
ff631b7838 [Server] Support encrypt & auth for FD Server (#2018) 
* [Server] Support GPU encrypt & auth for FD Triton Server

* fix dockerfile proxy env error

* update build scrpits

* remove some logs

---------

Co-authored-by: root <root@yq02-sys-rpm1206692e6.yq02.baidu.com>
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com>
 2023-06-13 20:44:25 +08:00
Jason
73f42e36be [Pybind] Try to fix xpu with Set External Data support copy (#2022) 
Set External Data support copy
 2023-06-09 15:47:40 +08:00
YuBinglei
5f9e8b6e08 [Bug Fix] Re-Fix OCR Serving bug. #1516 (#2011) 
see https://github.com/PaddlePaddle/FastDeploy/pull/1516

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-06-09 13:44:55 +08:00
Wang Bojun
7b58387d3c add option for inference precision and cutlass (#2017) 
* add option for inference precision and cutlass

* code clean

* code refine

* code refine
 2023-06-09 10:20:48 +08:00
DefTruth
147060ac60 [benchmark] add paddlex benchmark run scripts (#2015) 2023-06-05 23:19:05 +08:00
Zheng-Bicheng
8d357814e8 [Backend] Add pybind & PaddleDetection example for TVM (#1998) 
* update

* update

* Update infer_ppyoloe_demo.cc

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-06-04 13:26:47 +08:00
CoolCola
c634a9260d [Benchmark] support CLIP and DINO (#2014) 
* support ocrv4 det

* add clip dino
 2023-06-02 19:01:56 +08:00
CoolCola
05b3c1febd [Benchmark]support ocrv4 det (#2013) 
support ocrv4 det
 2023-06-02 17:32:29 +08:00
DefTruth
126ac9e915 [Bug Fix] fixed runtime benchmark bin error (#2010) 2023-06-02 14:45:31 +08:00
DefTruth
de8f0fe1f2 [Cherry Pick][benchmark] Pick PaddleX benchmark codes from <- paddlex (#2009) 
[benchmark] add paddlex benchmark codes
 2023-06-02 11:14:49 +08:00
DefTruth
284b1b46c8 [Serving] Support XPU encrypt & auth server (#2007) 
* [patchelf] fix patchelf error for inference xpu

* [serving] add xpu dockerfile and support fd server

* [serving] add xpu dockerfile and support fd server

* [Serving] support XPU + Tritron

* [Serving] support XPU + Tritron

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] add comments for xpu tritron dockerfile

* [Doruntime] fix xpu infer error

* [Doruntime] fix xpu infer error

* [XPU] update xpu dockerfile

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* [XPU] Update XPU L3 Cache setting docs

* [XPU] Add Encryption and AUTH support for XPU Server

* [XPU] Add Encryption and AUTH support for XPU Server

* [Bug Fix] fix paddle reader error

* [Serving] Support XPU encrypt & auth server

* [Serving] Support XPU encrypt & auth server

* [Serving] Support XPU encrypt & auth server

* [Serving] Support XPU encrypt & auth server

* [Triton] switch TAG 22.12 -> TAG 21.10wq

* update xpu auth server script
 2023-06-01 21:36:44 +08:00
DefTruth
387c5695b3 [XPU] Update XPU L3 Cache setting docs (#2001) 
* [patchelf] fix patchelf error for inference xpu

* [serving] add xpu dockerfile and support fd server

* [serving] add xpu dockerfile and support fd server

* [Serving] support XPU + Tritron

* [Serving] support XPU + Tritron

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] add comments for xpu tritron dockerfile

* [Doruntime] fix xpu infer error

* [Doruntime] fix xpu infer error

* [XPU] update xpu dockerfile

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* [XPU] Update XPU L3 Cache setting docs
 2023-05-30 11:21:04 +08:00
DefTruth
434b48dda5 [Serving] Support FastDeploy XPU Triton Server (#1994) 
* [patchelf] fix patchelf error for inference xpu

* [serving] add xpu dockerfile and support fd server

* [serving] add xpu dockerfile and support fd server

* [Serving] support XPU + Tritron

* [Serving] support XPU + Tritron

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0

* [Dockerfile] add comments for xpu tritron dockerfile

* [Doruntime] fix xpu infer error

* [Doruntime] fix xpu infer error

* [XPU] update xpu dockerfile

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* add xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs

* update xpu triton server docs
 2023-05-29 14:38:25 +08:00
co63oc
3a9904411a [C API] Fix some c api document typos (#1997) 2023-05-29 13:43:54 +08:00
Zheng-Bicheng
643730bf5f [Hackathon 181] Add TVM support for FastDeploy on macOS (#1969) 
* update for tvm backend

* update third_party

* update third_party

* update

* update

* update

* update

* update

* update

* update

* update

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-25 19:59:02 +08:00
DefTruth
49c033a828 [XPU] Support XPU via Paddle Inference backend (#1987) 
* [backend] Support XPU via Paddle Inference backend

* [backend] Support XPU via Paddle Inference backend

* [backend] Support XPU via Paddle Inference backend

* [XPU] support XPU benchmark via paddle inference

* [XPU] support XPU benchmark via paddle inference

* [benchmark] add xpu paddle h2d config files
 2023-05-25 14:13:40 +08:00
Zeref996
24f32d10a7 [Docs] refresh fd version 1.0.7 (#1986) 2023-05-24 17:35:26 +08:00
DefTruth
2672e2b881 [benchmark] optimize benchmark bin options (#1984) 
* [benchmark] optimize benchmark bin options

* [benchmark] optimize benchmark bin options
 2023-05-24 14:56:00 +08:00
WJJ1995
9a5b291f60 [Serving]Fixed dockerfile (#1978) 
* add workspace_size option

* support 11.2 cuda

* fixed dockerfile

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-23 16:22:53 +08:00
WJJ1995
ee81605e5d [Serving]Support 11.2 CUDA (#1976) 
* add workspace_size option

* support 11.2 cuda

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-23 15:16:07 +08:00
heliqi
3e7cb88049 [Serving]support 22.12 (#1974) 
support 22.12
 2023-05-22 22:27:13 +08:00
Zheng-Bicheng
1ac6e8e614 [Shell] support fastdeploy_init.sh for MacOS (#1967) 
* 兼容zsh

* 使用脚本所在的绝对路径, 确保与执行位置无关

* * Fixed the naming error of the LIBS_DIRECOTRIES variable.
* Fixed the error of using '=' for string comparison.

* * Troubleshooting failed environment variable addition on macOS system

---------

Co-authored-by: Edward Zhou <edwardzhou@EdwarddeMacBook-Pro-2.local>
Co-authored-by: Edward Zhou <edward.zhq@gmail.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-19 17:30:12 +08:00
Edward Zhou
2032ce8dca [Shell] Support fastdeploy_init.sh for ZSH terminal (#1684) 
* 兼容zsh

* 使用脚本所在的绝对路径, 确保与执行位置无关

---------

Co-authored-by: Edward Zhou <edwardzhou@EdwarddeMacBook-Pro-2.local>
Co-authored-by: Zheng-Bicheng <58363586+Zheng-Bicheng@users.noreply.github.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-19 16:51:51 +08:00
DefTruth
f21f2b3dee [cmake] bump up paddle2onnx -> 1.0.7 (#1966) 
* Update paddle2onnx.cmake

* re-run CIs

* [Bug Fix] fix fd+paddle2.4.2 serving build script error
 2023-05-19 16:38:52 +08:00
WJJ1995
92fcee6c3b [Serving] Add trt workspace_size option for serving (#1963) 
add workspace_size option

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-19 11:29:58 +08:00
CoolCola
e3b285c762 [Model] Support Paddle3D PETR v2 model (#1863) 
* Support PETR v2

* make petrv2 precision equal with the origin repo

* delete extra func

* modify review problem

* delete visualize

* Update README_CN.md

* Update README.md

* Update README_CN.md

* fix build problem

* delete external variable and function

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-19 10:45:36 +08:00
linkk08
c8ff8b63e8 [XPU] Add docs for gm_default_size and fix type (#1962) 
Add description of gm_default_size and change kunlunxin_gm_default_size‘s type to int64_t
 2023-05-18 20:30:06 +08:00
DefTruth
04ef882ee1 [Bug Fix] fix extra version info error (#1959) 2023-05-18 13:25:04 +08:00
DefTruth
b080b90f80 [python] support build paddle2onnx code for python & custom url (#1956) 
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
 2023-05-18 11:40:07 +08:00
DefTruth
1f66d5d9d3 [benchmark] support lite light api & optimize benchmark flags (#1950) 
* [benchmark] support lite light api & optimize benchmark flags

* [backend] remove un-used option member

* [backend] remove un-used option member
 2023-05-17 18:51:32 +08:00
Qianhe Chen
09ec386e8d [Bug Fix] Fix speech and silence state transition in VAD (#1937) 
* Fix speech and silence state transition

* Fix typo

* Fix speech and silence state transition

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-16 18:50:04 +08:00
linkk08
9ed8d18fcc [XPU] Add gm_default_size -> Backend::LITE (#1934) 
* add gm_default_size

* add gm_default_size

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-16 14:31:22 +08:00
DefTruth
33e07410da [cmake] Support custom paddle inference url (#1939) 
* [cmake] Support custom paddle inference url

* [Python] Add custom Paddle Inference URL support for python

* [Docker] Add fd serving Dockerfile for paddle2.4.2

* [Docker] Add fd serving Dockerfile for paddle2.4.2

* [Docker] Add fd serving Dockerfile for paddle2.4.2

* [Docker] Add fd serving Dockerfile for paddle2.4.2

* [Bug Fix] fixed result format string error

* rerunning the re-touch CIs

* rerunning CIs
 2023-05-16 14:30:31 +08:00
DefTruth
a5a7c962d0 [benchmark] Add lite opencl gpu option support (#1944) 
[benchmark] add lite opencl gpu option support
 2023-05-15 20:41:10 +08:00
linyangshi
b12d330076 [Bug Fix] Fix get_models bug (#1943) 
* 添加paddleclas模型

* 更新README_CN

* 更新README_CN

* 更新README

* update get_model.sh

* update get_models.sh

* update paddleseg models

* update paddle_seg models

* update paddle_seg models

* modified test resources

* update benchmark_gpu_trt.sh

* add paddle detection

* add paddledetection to benchmark

* modified benchmark cmakelists

* update benchmark scripts

* modified benchmark function calling

* modified paddledetection documents

* upadte getmodels.sh

* add PaddleDetectonModel

* reset examples/paddledetection

* resolve conflict

* update pybind

* resolve conflict

* fix bug

* delete debug mode

* update checkarch log

* update trt inputs example

* Update README.md

* add ppocr_v4

* update ppocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

* update get_models.sh

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-15 16:02:59 +08:00
unseenme
3fd21c935e [Hackthon_4th 244] Added Paddle Lite GPU Backend (#1907) 
* [improved] enum; ConfigureGpu();

* [improved] init()

* [improved] valid place; model dir; is valid;

* [added] WITH_OPENCL in cmake

* [improved] set model; valid place; cmake url; cmake option;

* Update runtime_option.cc

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-12 19:44:27 +08:00
DefTruth
15c29f7e49 [Python] Add backward compatible for paddle2.4.2 (#1929) 
* [Python] Add backward compatible for paddle2.4.2

* [Python] Add backward compatible for paddle2.4.2

* [scripts] update linux build scripts
 2023-05-11 19:34:06 +08:00
linyangshi
643f41e711 [Model] Support PP-OCRv4 pipeline (#1913) 
* 添加paddleclas模型

* 更新README_CN

* 更新README_CN

* 更新README

* update get_model.sh

* update get_models.sh

* update paddleseg models

* update paddle_seg models

* update paddle_seg models

* modified test resources

* update benchmark_gpu_trt.sh

* add paddle detection

* add paddledetection to benchmark

* modified benchmark cmakelists

* update benchmark scripts

* modified benchmark function calling

* modified paddledetection documents

* upadte getmodels.sh

* add PaddleDetectonModel

* reset examples/paddledetection

* resolve conflict

* update pybind

* resolve conflict

* fix bug

* delete debug mode

* update checkarch log

* update trt inputs example

* Update README.md

* add ppocr_v4

* update ppocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-11 16:09:50 +08:00
DefTruth
e75e766b19 [Lite] Bump up Paddle Lite -> latest 0.0.0.ab000121e (#1925) 2023-05-10 14:22:57 +08:00
DefTruth
ad9c70675e [tests] Update cpp release tasks scripts (#1918) 
[tests] Update release tasks scripts
 2023-05-09 17:14:06 +08:00
DefTruth
27a8c897ab [Lite] Support custom Paddle-Lite lib setting (#1906) 2023-05-08 14:05:43 +08:00
DefTruth
77cb9db6da [Model] Support PP-ShiTuV2 models for PaddleClas (#1900) 
* [cmake] add faiss.cmake -> pp-shituv2

* [PP-ShiTuV2] Support PP-ShituV2-Det model

* [PP-ShiTuV2] Support PP-ShiTuV2-Det model

* [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support

* [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support

* [Bug Fix] fix ppshitu_pybind error

* [benchmark] Add ppshituv2-det c++ benchmark

* [examples] Add PP-ShiTuV2 det & rec examples

* [vision] Update vision classification result

* [Bug Fix] fix trt shapes setting errors
 2023-05-08 14:04:09 +08:00
seyosum
df8dd3e3ac 【Hackthon_4th 180】Support HORIZON BPU Backend for FastDeploy (#1822) 
* add horizon backend and PPYOLOE examples

* 更改horizon头文件编码规范

* 更改horizon头文件编码规范

* 更改horizon头文件编码规范

* 增加horizon packages下载及自动安装

* Add UseHorizonNPUBackend Method

* 删除编译FD SDK后多余的头文件,同时更改部分规范

* Update horizon.md

* Update horizon.md

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-06 16:10:37 +08:00
linyangshi
9164796645 [Model] Support DINO & DETR and add PaddleDetectionModel class (#1837) 
* 添加paddleclas模型

* 更新README_CN

* 更新README_CN

* 更新README

* update get_model.sh

* update get_models.sh

* update paddleseg models

* update paddle_seg models

* update paddle_seg models

* modified test resources

* update benchmark_gpu_trt.sh

* add paddle detection

* add paddledetection to benchmark

* modified benchmark cmakelists

* update benchmark scripts

* modified benchmark function calling

* modified paddledetection documents

* add PaddleDetectonModel

* reset examples/paddledetection

* resolve conflict

* update pybind

* resolve conflict

* fix bug

* delete debug mode

* update checkarch log

* update trt inputs example

* Update README.md

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-05-05 14:10:33 +08:00
DefTruth
6d0261e9e4 [Model] Support PP-StructureV2-Layout model (#1867) 
* [Model] init pp-structurev2-layout code

* [Model] init pp-structurev2-layout code

* [Model] init pp-structurev2-layout code

* [Model] add structurev2_layout_preprocessor

* [PP-StructureV2] add postprocessor and layout detector class

* [PP-StructureV2] add postprocessor and layout detector class

* [PP-StructureV2] add postprocessor and layout detector class

* [PP-StructureV2] add postprocessor and layout detector class

* [PP-StructureV2] add postprocessor and layout detector class

* [pybind] add pp-structurev2-layout model pybind

* [pybind] add pp-structurev2-layout model pybind

* [Bug Fix] fixed code style

* [examples] add pp-structurev2-layout c++ examples

* [PP-StructureV2] add python example and docs

* [benchmark] add pp-structurev2-layout benchmark support
 2023-05-05 13:05:58 +08:00
thunder95
2c5fd91a7f [Hackthon_4th 242] Support en_ppstructure_mobile_v2.0_SLANet (#1816) 
* first draft

* update api name

* fix bug

* fix bug and

* fix bug in c api

* fix bug in c_api

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-04-27 10:45:14 +08:00
DefTruth
ef576ce875 [Paddle2ONNX] switch paddle2onnx default policy (#1873) 2023-04-26 10:32:18 +08:00