Skip to content

segmentation algorithm yolact use tensorrt deploy

Notifications You must be signed in to change notification settings

nanmi/yolact-trt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

YOLACT-TensorRT in C++

our repo base on pytorch version of yolact https://github.com/dbolya/yolact.git

Step 0: Install some dependency package

Install opencv with sudo apt-get install libopencv-dev.

Step 1: Export onnx form pytorch yolact

reference: https://medium.com/@nanmi/%E5%A6%82%E4%BD%95%E7%94%A8tensorrt%E9%83%A8%E7%BD%B2yolact-3690e0708a85

Step 2: Generate yolact engine for tensorrt

Please follow the TensorRT trtexec tools to genetate TensorRT engine.

Step 3: Build our project and inference yolact engine

build the demo:

mkdir build
cd build
cmake ..
make

Then run the demo:

./yolact ../yolac_fp32.engine -i ../000000000016.jpg

or

./yolact <path/to/your/engine_file> -i <path/to/image>

About License

For the 3rd-party module and Deepstream, you need to follow their license

For the part I wrote, you can do anything you want

About

segmentation algorithm yolact use tensorrt deploy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published