haotian/duan8
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
343 Commits 2 Branches 0 Tags 7.8 MiB
9071fa2d2b
Commit Graph

343 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
wang-xinyu
9071fa2d2b unet fix coding style 2022-11-25 21:42:01 +08:00
Wang Xinyu
e061888ed2 Update unet readme 2022-11-25 21:29:46 +08:00
wang-xinyu
e94e4ed70f unet support trt8 2022-11-25 21:13:49 +08:00
jinlj
1512aa73ae Add yolop_trt.py (#1131) 
* add simplified Logger class

* add modified yolop tensorrtx implementation

* add gen_wts.py

* add CMakeLists.txt

* add yolop tensorrtx README.md

* fix yolop spelling

* simplify yolop code

* fix yolop README.md

* Update README.md

* Add yolop_trt.py

* Update yolop README.md

* simplify yolop_trt.py

Co-authored-by: aliceint(zhanglj) <2464313547@qq.com>
Co-authored-by: Wang Xinyu <wangxinyu_es@163.com>
 2022-11-01 19:21:12 +08:00
Wang Xinyu
9243edf59e Update README.md 2022-10-26 20:26:54 +08:00
Wang Xinyu
9253d58e7a Update README.md 2022-10-26 15:18:08 +08:00
jinlj
208b2fcf39 Feature: add modified yolop tensorrt implementation (#1129) 
* add simplified Logger class

* add modified yolop tensorrtx implementation

* add gen_wts.py

* add CMakeLists.txt

* add yolop tensorrtx README.md

* fix yolop spelling

* simplify yolop code

* fix yolop README.md

Co-authored-by: aliceint(zhanglj) <2464313547@qq.com>
 2022-10-26 15:04:27 +08:00
wang-xinyu
0c78095dd6 lenet5: support trt8 2022-10-09 11:30:31 +08:00
Wang Xinyu
87f897bced Merge pull request #1117 from LiberiFatali/master 
Attach the decode kernel to the same CUDA stream
 2022-10-09 10:54:12 +08:00
LiberiFatali
569cc4a438 Attach the decode kernel to the same CUDA stream 
fix to load engine file in DeepStream 6.1.1
 2022-10-08 21:41:35 +07:00
wang-xinyu
dfc437daa0 fix coding style 2022-09-29 18:48:29 +08:00
wang-xinyu
1c65f082e0 fix coding style 2022-09-23 16:03:40 +08:00
wang-xinyu
4079560f95 fix code style 2022-09-23 15:43:36 +08:00
wang-xinyu
ccbf1170b9 yolov7 samples soft link 2022-09-23 15:34:08 +08:00
lindsayshuo
dc1e279516 update gen_wts.py and some yolov5's names (#1109) 
* update gen_wts.py and some yolov5's names

* Update gen_wts.py
 2022-09-22 11:03:37 +08:00
Wang Xinyu
ca5e9425f9 Update README.md 2022-09-19 16:02:00 +08:00
Wang Xinyu
fb674add10 Update README.md 2022-09-19 15:55:49 +08:00
lindsayshuo
64da26ef5d yolov7 v0.1 (#1105) 
* yolov7 v0.1

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update yololayer.h

* Update yololayer.h

* Delete yolov7.engine

* Delete yolov7-tiny.engine

* Delete yolov7/output directory

* Delete dirent.h

* Update README.md

* Update README.md

* Update README.md

* Update README.md
 2022-09-19 15:49:39 +08:00
Wang Xinyu
d988519e73 Update README.md 2022-09-07 16:53:57 +08:00
wang-xinyu
10fd212890 update readme 2022-09-07 15:36:03 +08:00
wang-xinyu
b8d8c8ab92 yolov5 cls cpp postprocessing 2022-09-07 14:58:12 +08:00
wang-xinyu
2c0c7539e3 yolov5 cls cpp inference 2022-09-06 20:35:26 +08:00
wang-xinyu
e5a0573dde add gen wts choices 2022-09-06 19:52:31 +08:00
Xiang Shin Wuu
fdd6a76ec2 Yolov5 classification model support (#1082) 
* updated gen_wts script to support yolov5 classfication model export

* updated yolov5-s architecture to support classification head.

* updated yolov5_trt infer script to support yolov5 classification model alongwith existing detection model.

* added imagenet_classes file to load list of 1k classes required for the infer script.

* final conv block doesn't require dynamic scale factor for out channel, hence hardcoded value provided to support all model varients

* yolov5.cpp reverted back to original state, with explicit code changes

* python infer script reverted back to prior state, with explicit code changes

* seperate cpp file added for yolov5 classification task

* cmake updated for yolo5 classification file

* seperate python infer script for classification task

* cmake updated by replacing cuda_add_executable with add_executable

* default value added to the type argument

* post-processing removed from yolov5 clasisifcation module

* pre-processing for yolov5 classification inferencing

* classification macro removed from the original yolov5 detection cpp file

* reverted some extremely minor formatting changes.

* reverted back to prior state by removing all formatting changes.
 2022-08-30 18:52:34 +08:00
Wang Xinyu
8112542b5f
Update README.md 2022-08-19 18:07:10 +08:00
Subtain Malik
3accb0d8e2
Arcface trt8 (#1076) 
* gen_weights for latest pretrained_models

* tensorrt-8 migrations

* updated docs
 2022-08-19 17:55:08 +08:00
Dominic D
46dccf11ea
Update YOLOv3-tiny for TRT8 (#1064) 
* Update YOLOv3-tiny for TRT8
Changes from #967

* Also apply fixes to utils

* Remove redundant macro definition in logging.g
 2022-08-02 13:33:13 +08:00
Wang Xinyu
0f944b8975
Update README.md 2022-07-06 11:35:17 +08:00
Xiang Shin Wuu
fdd136466f
SuperPoint TensorRT implementation (#1034) 
* adding tensorrt implementation of superpoint network.

* inference output result & todo list added to README
 2022-07-06 11:19:10 +08:00
Egor Tolmachev
dbdad6846c
Fix comparison with args in mode check. (#1019) 
@wang-xinyu @wdhao  Before we had assignment, not comparison.(somebody forgot "=" but not only)
 2022-06-27 13:51:24 +08:00
haku
e418cb9e66
add dockerfile trt8_cuda11 (#1010) 
* add dockerfile trt8_cuda11

* update docker readme
 2022-06-11 11:51:41 +08:00
HaiyangP
6636cc26fd
Modifications in rcnn.cpp for more applicable outputs of instance segmentation. (#946) 
* Support to output the instance segmentation results on an original input image, rather than on a padded one.

* modifications according to freedenS's suggestions

* modification for padding

* merge preprocessImg and preprocessImg_ and delete all the debug codes.

* bug of reference passing

* make the vars consistent with the previous rcnn.cpp and update the README

Co-authored-by: benkang wang <benkang.wang@uisee.com>
 2022-06-06 11:03:28 +08:00
Wang Xinyu
e2f270a0ce
Update README.md 2022-05-28 07:59:05 +08:00
Wang Xinyu
6c59b8bc26
Update README.md 2022-05-27 08:44:34 +08:00
Wang Xinyu
b91b15d3e7
Update README.md 2022-05-27 08:38:03 +08:00
tripleMu
bfe0b55406
Replace pycuda api with cuda-python (#1002) 
* Replace cuda-python api of pycuda

* Remove my test batch=2
 2022-05-26 09:37:06 +08:00
Wang Xinyu
f80f010ac4
Update README.md 2022-05-23 10:44:07 +08:00
Wang Xinyu
3705a1a095
fix typo 2022-05-23 10:32:59 +08:00
Wang Xinyu
8a472a1c6d
Update README.md 2022-05-23 10:30:57 +08:00
yhpark
e0c5243a53
added real-esrgan (#999) 
* added real-esrgan

* deleted sample image & modified README

* tab to space
 2022-05-23 10:14:05 +08:00
Vijaysrinivas Rajagopal
42b4f94527
YOLOv3 TRT8 support 
* yolov3 trt8 fix

* move the if,else to macro header like yolov5

* reset imagesize to 608 and other stuff
 2022-05-19 14:28:54 +08:00
Wang Xinyu
6ddff90025
Update README.md 2022-03-15 13:02:50 +08:00
Wang Xinyu
e7ec22d8b8
add swin-transformer (#934) 
* add swin-transformer

* change dir

* reformat

* fix gen wts and polish readme

Co-authored-by: wdhao <873665182@qq.com>
 2022-03-15 12:10:49 +08:00
tripleMu
3f31d76ac4
Fix bug (#931) 
Co-authored-by: tripleMu <92794867+q3394101@users.noreply.github.com>
 2022-03-11 13:45:56 +08:00
AdanWang
70059d1802
modify load model for ema (#929) 
Co-authored-by: 王光强 <wangguangqiang@cethik.com>
 2022-03-11 13:44:17 +08:00
LW-SCU
c2a07ff7ac
Fix wrong use of copyMakeBorder (#883) 
Co-authored-by: lwjustsoso <351048599@qq.com>
 2022-01-28 11:34:59 +08:00
Subtain Malik
f2ac76df5a
added MLP with proper documentation (#874) 
* [MLP]: create using core TensortRT python APIs

* [MLP]: README.md added with chart

* [MLP]: C++ TensorRT APIs added

* [MLP]: Updated Docs

* [MLP]: basic .wts added with APIs

* [MLP]: Updated minor details

* [MLP]: fix
 2022-01-10 11:34:23 +08:00
Vijaysrinivas Rajagopal
e6b22917e6
YOLOv3 TRT Python (#873) 
* change yolov5_trt to fit yolov3 output

* change ref from yolov5 to v3
 2022-01-07 11:09:48 +08:00
xupengao
5f1b048a29
fix bug (#808) 
* Add files via upload

* check_file

* remove invalid data

* remove data

* Optimization and modification

add all  yolo model

* fix bug

* fix bug

Co-authored-by: Wang Xinyu <wangxinyu_es@163.com>
 2021-11-09 13:53:20 +08:00
Silmeria112
befdf6ee64
update gen_wts.py for yolov5 to support custom model with different anchor from official model(#788) 2021-10-29 11:10:12 +08:00