This jupyter notebook trains a donkeycar repository of images to identify corresponding steering and throttle values using fastai V2. I have added a transform to augment image inputs by mirroring the image and complementing the steering value. The whole thing runs in under 10 minutes on my laptop.
-
Notifications
You must be signed in to change notification settings - Fork 0
Training of a donkeycar repository using fastai V2.
License
cmasenas/fastai_navigation_training
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Training of a donkeycar repository using fastai V2.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published