search

AlexeyAB / yolo2_light

Light version of convolutional neural network Yolo v3 & v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference)
MIT License
302 stars 116 forks source link

ROS implementation #72

Open cedros23 opened 5 years ago

cedros23 commented 5 years ago

Hello,

Thanks for the great work. There is a significant efficiency of inference in Nvidia px2. I am considering a ROS implementation, do you think any obstacle due to dependencies etc.?

I have something like below in my mind: https://github.com/leggedrobotics/darknet_ros

Thanks, Regards, Ugur

cedros23 commented 5 years ago

I have just found there is one repo with the original Alexeyab Yolo: https://github.com/pushkalkatara/darknet_ros

So the question is, I should rephrase, does quantization and xnor updates would cause problem for ROS?

I will keep digging and update here.

Thanks again