6 Commits

Author SHA1 Message Date
hanrui1sensetime
6948e3d04b
Ncnn demo sdk (#164)
* fix different dims and data sync and fp16 macro

* fix pad is negative bug, but still need debugging info

* split detection_output to dets and labels

* fix clang++ compile bug

* for fp16 compile macro of cmake

* fix pad_val dict input

* fix yolox missing normalization and get int tensor

* about score_threshold

* remove -lstdc++fs for android

* move -pthread for android

* fix link libraries for CLANG++;

* fix clang-format

* for mobileyolov3 conf_thre

* fix lint

* fix bug

* support ncnn vulkan net

* remove unused debugging info;

* Change INFO to DEBUG

* support vulkan precision mapping

* fix pad

* optimize getdetslabels

* remove EVAL_MODE

* ncnn_net support 4-dim data.

* remove FP16 compile options

* remove use_gpu_vulkan compile options

* fix pad.cpp

* fix yapf

* fix clang-format

* rm redundant lines

* fix pad according to mmdet

* add android build docs

* fix lint

* use cpp style string comparision

* fix use after free bug

* Add missing -DBUILD_SHARED_LIBS=OFF for en

* Add missing -DBUILD_SHARED_LIBS=OFF for ZH-CN

* reset img2tensor_impl

* reset img2tensor_impl

* add blank line

* sync android.md docs

* fix some dirs

* fix docs

* update docs

* fix code
2022-03-25 23:28:16 +08:00
lzhangzz
640aa03538
Support Windows (#106)
* minor changes

* support windows

* fix GCC build

* fix lint

* reformat

* fix Windows build

* fix GCC build

* search backend ops for onnxruntime

* fix lint

* fix lint

* code clean-up

* code clean-up

* fix clang build

* fix trt support

* fix cmake for ncnn

* fix cmake for openvino

* fix SDK Python API

* handle ops for other backends (ncnn, trt)

* handle SDK Python API library location

* robustify linkage

* fix cuda

* minor fix for openvino & ncnn

* use CMAKE_CUDA_ARCHITECTURES if set

* fix cuda preprocessor

* fix misc

* fix pplnn & pplcv, drop support for pplcv<0.6.0

* robustify cmake

* update build.md (#2)

* build dynamic modules as module library & fix demo (partially)

* fix candidate path for mmdeploy_python

* move "enable CUDA" to cmake config for demo

* refine demo cmake

* add comment

* fix ubuntu build

* revert docs/en/build.md

* fix C API

* fix lint

* Windows build doc (#3)

* check in docs related to mmdeploy build on windows

* update build guide on windows platform

* update build guide on windows platform

* make path of thirdparty libraries consistent

* make path consistency

* correct build command for custom ops

* correct build command for sdk

* update sdk build instructions

* update doc

* correct build command

* fix lint

* correct build command and fix lint

Co-authored-by: lvhan <lvhan@pjlab.org>

* trailing whitespace (#4)

* minor fix

* fix sr sdk model

* fix type deduction

* fix cudaFree after driver shutting down

* update ppl.cv installation warning (#5)

* fix device allocator threshold & fix lint

* update doc (#6)

* update ppl.cv installation warning

* missing 'git clone'

Co-authored-by: chenxin <chenxin2@sensetime.com>
Co-authored-by: zhangli <zhangli@sensetime.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
Co-authored-by: lvhan <lvhan@pjlab.org>
2022-02-24 20:08:44 +08:00
lvhan028
c74c41bec9
Fix memleak (#86)
* delete []

* fix build error when enble MMDEPLOY_ACTIVE_LEVEL

* fix lint
2022-01-20 15:21:19 +08:00
lzhangzz
56e32fdf63
improve shape checking (#315) 2021-12-21 20:16:40 +08:00
lzhangzz
43e6714f47
[SDK] Fix asan errors (#308)
* fix several heap-use-after-free bugs

* rebase master

* add option for sanitizers

* rebase master

* fix conflicts
2021-12-21 10:47:21 +08:00
lzhangzz
a494a6f6ff
[SDK] sync changes according to performance benchmarks (#297)
* sync SDK changes according to performance benchmarks

* fix end-of-file lint

* fix clang-format issue

* fix clang-format by adding 'clang-format off'

* remove useless casts

* remove 'data' argument of 'operator()'

* change 'Tensor2Img' to 'TensorToImg' according to spec

* correct tensor's name according spec

Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-16 13:51:22 +08:00