Viewing profile — wroscoe

I updated this post with some of the great feedback from the comments. Also I just ported the algo used by the last DIYRobocar race winner, CompoundEye. Here's that post: https://w…

Well shit. Thanks for pointing that out. I'll revise.

The input values are image arrays 120x160 pixels with 3 channels for red,green,blue. The values range from 0-255 and are not normalized before they are fed into the convolution lay…

Tensorflow anounced last week that it will incorporate Keras as its default higher level abstraction. It's a pleasure to use.

Traditional CV approaches are much easier to debug as well. I chose the ML approach with the assumption that it would be easier to build a robust autopilot that would work in many …

Yep, this was an exercise to compete in the DIYRobocars race in West Oakland last weekend. There were 9ish cars with 7 running end to end Tensorflow autopilots and the others using…

I'm working on adding the throttle. This is difficult because you need to drive the correct speed and stopping or running off course can mess up the training data. This project was…

The method to avoid overfitting was to use the model with the lowest validation loss, not training loss. I was able to change the track around my house with reasonable success. I t…

I copied this method of loading datasets from Keras. https://github.com/fchollet/keras/blob/master/keras/datasets... . What's a better alternative.

Donkey runs a client on the Pi and a remote server that runs Keras/Tensorflow.