Ed Murphy
Ed Murphy
I really like this direction. I really like that the user could spin-up a vehicle without needing any Python or even a configuration file. There a few things to think...
I know @TCIII uses the PS4 on Nano. He was having this issue.
@DocGarbanzo Thank you for the review, I've rebased and updated version="4.3.20"
@TCIII we are at donkey 4.4 now. Can we close this issue?
I'm going to close this. Both Tensorflow and Tensorflow Lite support multi-threaded inference. Here is Google's page on how to profile a model and the levers for increasing performance, including...
docs have been updated https://docs.donkeycar.com/parts/controllers/#ps4-dualshock-4-wireless-gamepad-controller
T265 is not longer suppored by Intel, so I'm going to close this issue.
Now that we have completed upgrading the computer vision template (cv_control.py) and the path follow template (path_follow.py) it seems reasonable to remove the other templates.
@DocGarbanzo also implemented an improvement to caching when using augmentation in PR https://github.com/autorope/donkeycar/pull/1050 Total training time on my RTX-2060 went from 2.5 hours to 45 minutes for 21 epochs
This can be done in the DonkeyUI in the [Pilot Arena](https://docs.donkeycar.com/utility/ui/#the-pilot-arena)