Commit Graph

246 Commits

Author SHA1 Message Date
JumpPandaer
2c4fdea67d
update rcnn (#521)
* add MaskRcnn(C4)

* add MaskRcnnInference plugin for mask selecting

* split ROIHeads to BOXHead and MaskHead

* remove unuseful parameters in createEngine_rcnn and BuildRcnnModel

* change the type of scores_h, boxes_h and classes_h from unique_ptr to vector

* add doInference

* add maskrcnn postprocess

* update README.md

* update rcnn

* fix bugs with R18 and R34
 add BasicBlock for R18 and R34
 add STRIDE_IN_1X1, MakeStage is same with detectron2 now.

* update README.md

* update rcnn

replace picture with url
2021-05-07 10:50:55 +08:00
makaveli
f4c384d1b1
add: Scaled yolov4 (#524)
* add: mish, yololayer, layers

* update: CMake

* fix: compile

* add: yolov4-csp net def

* update: cuda kernel for scaled_yolov4

* increase nms thresh

* update: README

* add: gen_wts

* update: CMake

* fix memory leak

* Update README.md

* Update README.md

* Update README.md

* Update README.md
2021-05-06 11:05:20 +08:00
Aditya Lohia
4ffc56a99b
Add: Wideresnet (#4) (#518)
* Adding WideResnet C++  (#2)

* initialize wideresnet50

* add: wideresnet50 c++ code

* add: wide resnet python (#3)

* add: wide resnet python

* fix: typo

Co-authored-by: makaveli <39617050+makaveli10@users.noreply.github.com>

Co-authored-by: makaveli <39617050+makaveli10@users.noreply.github.com>
2021-04-30 10:30:40 +08:00
weiwei zhou
1f7672ce5a
add hrnet semantic segmentation model w18, w32 and w48 (#503)
* create psenet

create psenet with weight from tensorflow

* delete some useless code

* repalce tab with 4 blanks

* fix network bug, rewrite post-processing pse algorithm

* update readme

* update readme

* add RepVGG

* fix typo

* add hrnetseg w18 w32 w48

* add hrnetseg with ocr w18 w32 w48

* merge hrnet and small, add hrnet_ocr

* fix warning

* change project name
2021-04-29 20:26:15 +08:00
wwqgtxx
b58a7987bc
add a simple warm_up in yolov5_trt.py (#513)
* add a simple warm_up in yolov5_trt.py

* remove if-else condition in infer()

* be careful with bgr and rgb image
2021-04-28 17:37:38 +08:00
Aditya Lohia
e8653a776d
Add: AlexNet, MobileNetV3, DenseNet121 Python Network Definition API (#512)
* add: mobilenetv2 Python network definition API

* add: mobilenetv3 base code

* add: mobilenetv2 Python network definition API

* restructure: mobilenetv2 code

* add: Alexnet Python Network Definition API

* update: README according to new folder architecture

* add: mobilenetv3 small and large python network definition API

* add: DenseNet121 Python Network Definition API
2021-04-28 13:39:55 +08:00
wang-xinyu
acc8a26213 yolov5 fix readme 2021-04-28 05:34:13 +00:00
wang-xinyu
117a16e291 yolov5 .py batch processing 2021-04-27 13:00:05 +00:00
wang-xinyu
9b60aa240f Merge branch 'master' of https://github.com/wang-xinyu/tensorrtx 2021-04-27 08:39:48 +00:00
wang-xinyu
cb2aa5e72e yolov5 .py get w and h from engine 2021-04-27 08:39:14 +00:00
makaveli
64c4b43f2f
fix: typo (#509) 2021-04-27 11:05:55 +08:00
wang-xinyu
c9dfbf2f7c update readme 2021-04-26 12:29:44 +00:00
wang-xinyu
f088ec77d2 fix typo, add latency log 2021-04-26 11:38:57 +00:00
Aditya Lohia
bf1d851b5e
add: mobilenetv2 Python network definition API (#506)
* add: mobilenetv2 Python network definition API

* restructure: mobilenetv2 code
2021-04-26 14:04:22 +08:00
wang-xinyu
ad84d77335 update readme 2021-04-26 03:48:49 +00:00
wang-xinyu
9ff37c46ad Update directory structure 2021-04-26 03:17:35 +00:00
makaveli
4d630ed599
Inceptionv4 (#505)
* add: structure inception v4

* fix: camelcase naming

* fix and optimize

* add: doInference def

* define inception layers

* fix: spacing

* add: inception network def

* fix layers

* create net

* validate

* add README

* update readme

* typo

* create dir inception
2021-04-26 11:06:52 +08:00
wang-xinyu
046dd5b417 yolov5 support s6/m6/l6/x6 models 2021-04-25 12:17:15 +00:00
wang-xinyu
3e9a4fc19b verify yolov5 s/m/l/x and p6 backbone 2021-04-23 12:40:59 +00:00
wang-xinyu
e63a6a874f small fix of yolov5 2021-04-23 08:34:10 +00:00
irvingzhang0512
501160d262
Support TSM-R50 C++ API (#500)
* C++ API for TSM-R50

* fix bugs
2021-04-23 14:57:01 +08:00
JumpPandaer
8d8e2c9b0c
add MaskRcnn(C4) (#498)
* add MaskRcnnInference plugin for mask selecting

* split ROIHeads to BOXHead and MaskHead

* remove unuseful parameters in createEngine_rcnn and BuildRcnnModel

* change the type of scores_h, boxes_h and classes_h from unique_ptr to vector

* add doInference

* add maskrcnn postprocess

* update README.md
2021-04-23 10:42:22 +08:00
JumpPandaer
5d6b09cf5a
update rcnn (#495)
add pixel_std in preprocess
fix synchronization error in roialign and cudaMemcpyAsync
improve coding style, limit line length less than 120 and so on
update README.md
upgrade TensorRT to 7.2
2021-04-21 10:55:08 +08:00
irvingzhang0512
8cfc8ee03f
Support TSM-R50 Python API (#488)
* add tensorrt temporal shift module and related pytorch implementations

* add .gitignore and getn weights script.

* rename get_wts.py script

* Add tsm-r50 demo.

* update readme

* remove useless codes

* update readme

* update readme

* remote video and .gitignore, update tutorial

* update readme and tutorial

* fix a few bugs and test on tensorrt 5.1

* update readme
2021-04-18 16:30:25 +08:00
Wang Xinyu
d9bdd7e59f
Update README.md 2021-04-16 11:47:16 +08:00
JumpPandaer
891202d458
add FasterRcnn(R50C4) (#475)
* Update yolov5.cpp

implement upsample with IResizeLayer

* Update yolov5.cpp

repair mistake and test it

* add FasterRcnn(R50C4)

maskrcnn is working

* add FasterRcnn(R50C4)

adjust indent

* update README

adjust coding style
2021-04-16 11:41:18 +08:00
Pavel Mikhadzionak
e72d9db48b
Fix synchronization error (#485) 2021-04-16 10:37:10 +08:00
irvingzhang0512
7f17ce4f9b
Build ResNet50 by TensorRT Python Network Definition API (#482)
* add tensorrt python api sample for resnet50

* update docs

* typo

* fix typo

Co-authored-by: Wang Xinyu <shaywxy@gmail.com>
2021-04-15 13:17:41 +08:00
irvingzhang0512
3c5939cd0d
add tensorrt python api sample for lenet (#476) 2021-04-14 15:34:57 +08:00
irvingzhang0512
f54f113fe8
typo (#474) 2021-04-13 18:21:41 +08:00
PeterH0323
12f7c1b8b1
Improve DBNet README.md (#467)
* Fix: syntax error in common.hpp , cuda & tensorrt not included in CMakeLists.txt

* Fix: layer warining while building in common.hpp and denet.cpp

* Fix: NOT droping mini boxes and low score boxes.

* Fix: The prediction boxes are NOT expanded by the specified proportion, which will lead to serious errors

* Improve DBNet README

* Improve DBNet README

* Improve DBNet README
2021-04-08 10:52:33 +08:00
JumpPandaer
66d641814e
Update yolov5.cpp (#463)
* Update yolov5.cpp

implement upsample with IResizeLayer

* Update yolov5.cpp

repair mistake and test it
2021-04-07 18:08:25 +08:00
PeterH0323
b74db15d87
Optimize dbnet (#464)
* Fix: syntax error in common.hpp , cuda & tensorrt not included in CMakeLists.txt

* Fix: layer warining while building in common.hpp and denet.cpp

* Fix: NOT droping mini boxes and low score boxes.

* Fix: The prediction boxes are NOT expanded by the specified proportion, which will lead to serious errors
2021-04-07 17:54:27 +08:00
wang-xinyu
5b90354d28 fix genwts file close 2021-04-07 05:21:37 +00:00
wang-xinyu
4070131934 update readme 2021-04-02 09:44:28 +08:00
Vineet
5d72c5af87
Add DenseNet121 (#460)
* add: densenet

* update readme
2021-04-01 20:21:29 +08:00
mingyu6yang
e381ae5d20
Retinaface python (#458)
* Create retinaface_trt.py

An example that uses TensorRT's Python api to make inferences.

* Update retinaface_trt.py

* Update README.md
2021-03-31 15:06:12 +08:00
Wang Xinyu
a7f43a304d
Update README.md 2021-03-17 19:29:45 +08:00
wuzuowuyou
4b2ef40380
tensorRT RefineDet (#443) 2021-03-17 11:19:22 +08:00
wang-xinyu
1336337589 also use google drive for model zoo and calib data 2021-03-08 18:44:50 +08:00
Wang Xinyu
eb1accc869
Create stale.yml 2021-03-05 18:49:04 +08:00
Wang Xinyu
7bf3545678 Update issue templates 2021-03-05 17:19:00 +08:00
wang-xinyu
2ae0fd1882 update readme 2021-03-05 15:10:42 +08:00
alpha
2c2d3f28ad
add LPRNet (#430)
* upload LRPnet

* upload LPRnet

* upload LPRnet

* 1
2021-03-04 17:29:19 +08:00
Wang Xinyu
577ca20128
Update README.md 2021-03-02 17:35:20 +08:00
Wang Xinyu
6b2a139af7
Update README.md 2021-03-02 17:06:17 +08:00
wang-xinyu
8e4de7dced optimize yolov5 cmdline args 2021-02-28 14:30:15 +08:00
AsakusaRinne
fec5e618d4
Another way to build yolov5 engines (#416)
* Update yolov5.cpp

* Update README.md

* Update README.md
2021-02-28 11:25:36 +08:00
BaofengZan
37f03a77c5
fixed some issues (#400)
* 1 动态输入
2 图像预处理和后处理和pytorch同步
3 代码格式统一

* 重新梳理代码

* tab 替换为4 space

* HRNet-Semantic-Segmentation

* update result img

* update readme

* Synchronize

* Modify some bugs
2021-02-07 17:41:16 +08:00
weiwei zhou
b15a45da39
Fix typo which causes "addConvRule not declared" (#387)
* fix typo
2021-01-31 17:26:33 +08:00