[ros-users] [Discourse.ros.org] [Embedded] Deep Neural Network on Embedded?

[Ildoo Kim]

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.