Commit Graph

58 Commits

Author SHA1 Message Date
DefTruth
2613e9c5d0 [Android] support fastdeploy build with static deps(60Mb->29~31Mb) (#1176)
* [Android] support fastdeploy build with static deps(70Mb->17~19Mb)

* [Android] support fastdeploy build with static deps(60Mb->29~30Mb)

* fixed ci

* fixed ci

* [staticlib] support fd android static lib

* [static] optimize bundle_static_library func

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] Fixed Paddle Lite paddle_use_kernels.h to support fd armv7 static lib

* [staticlib] Add strip -> fd static lib target

* [staticlib] optimize bundle_static_library func

* [staticlib] add strip for fd static lib on  mac osx

* [staticlib] move api_helpers -> lite/option

* [staticlib] optimize bundle_static_library

* [staticlib] add Android limit
2023-01-30 19:39:56 +08:00
yeliang2258
829fe0721d [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116)
* add fp16 cuda kernel

* fix code bug

* update code
2023-01-13 19:44:00 +08:00
WJJ1995
aa6931bee9 [Model] Add YOLOv5-seg (#988)
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

* Add Monitor for benchmark

* update mem monitor

* Set trt_max_batch_size default 1

* fixed ocr benchmark bug

* support yolov5 in serving

* Fixed yolov5 serving

* Fixed postprocess

* update yolov5 to 7.0

* add poros runtime demos

* update readme

* Support poros abi=1

* rm useless note

* deal with comments

* support pp_trt for ppseg

* fixed symlink problem

* Add is_mini_pad and stride for yolov5

* Add yolo series for paddle format

* fixed bugs

* fixed bug

* support yolov5seg

* fixed bug

* refactor yolov5seg

* fixed bug

* mv Mask int32 to uint8

* add yolov5seg example

* rm log info

* fixed code style

* add yolov5seg example in python

* fixed dtype bug

* update note

* deal with comments

* get sorted index

* add yolov5seg test case

* Add GPL-3.0 License

* add round func

* deal with comments

* deal with commens

Co-authored-by: Jason <jiangjiajun@baidu.com>
2023-01-11 15:36:32 +08:00
Dantès
de70e8366c add ocr, ppyoloe, picodet examples (#1076)
* add ocr examples

* add ppyoloe examples

add picodet examples

* remove /ScaleFactor in ppdet/postprocessor.cc
2023-01-10 16:34:26 +08:00
Jason
fc314f1696 [Other] Rename directory op_cuda_kernels to common/cuda (#1104)
rename directory name
2023-01-10 16:31:37 +08:00
Jason
df20b2a02b [Other] Remove useless macros (#1095)
* Remove useless macros

* triger ci

* fix check error

* rename INTEGRATE_PADDLE2ONNX to ENABLE_PADDLE2ONNX
2023-01-09 21:35:23 +08:00
Jason
054dfec43a [Other] Remove some build options (#1090)
* remove some flags

* add gpu check in cmake
2023-01-09 17:36:07 +08:00
Jason
4aa4ebd7c3 [Other] [Part2] Upgrade runtime module (#1080)
[Other] Upgrade runtime module
2023-01-09 13:22:51 +08:00