I recently implement couple of algorithms for Deep Learning, which provides fast inference on an embedded devices.
One of them is called 'LCNN', you can find the original paper here :
https://arxiv.org/abs/1611.06473
And I implemented it with tensorflow,
https://github.com/ildoonet/tf-lcnn
This codes compress alexnet which takes roughly 150ms or more on a single core cpu,
to a sparse convolutional layered network which takes 10~50ms on the same environment.
![image|690x241](upload://xfPsVMENuBtzhvVRSCdo4OQRMwH.png)
https://github.com/ildoonet/tf-lcnn/raw/master/images/timeline_alexnet.png
So.. based on these new technologies, i am looking for an idea to try.
Like openpose on a robot :
https://discourse.ros.org/t/human-pose-estimation-deep-learning-model-openpose-ros-package/2407
Any Thoughts?
---
[Visit Topic](
https://discourse.ros.org/t/deep-neural-network-on-embedded/2604/1) or reply to this email to respond.
If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
ros-users@lists.ros.org
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <
http://lists.ros.org/mailman//options/ros-users>