View source for DonkeyCar for Pi-Train Data

==Guide of DonkeyCar==
*[[DonkeyCar for Pi-Setup Raspberry Pi|Setup Raspberry Pi]]
*[[DonkeyCar for Pi-Setup Linux PC|Setup Linux PC]]
*[[DonkeyCar for Pi-WEB Control|WEB Control]]
*[[DonkeyCar for Pi-Calibrate DonkeyCar|Calibrate DonkeyCar]]
*[[DonkeyCar for Pi-Teleoperation|Teleoperation]]
*[[DonkeyCar for Pi-Collect Data|Data Collection]]
*[[DonkeyCar for Pi-Train Data|Train Data]]
*[[DonkeyCar for Pi-Auto-Driving|Auto-Driving]]
*[[PiRacer Pro AI Kit|WiKi of PiRacer Pro]] | [[PiRacer AI Kit | WiKi of PiRacer]]

==Train Data==
:In a new terminal session on your host PC use rsync to copy your cars folder from the Raspberry P
<pre>
rsync -rv --progress --partial pi@<your_pi_ip_address>:~/mycar/data/  ~/mycar/data/
</pre>

==Train model==
:In the same terminal you can now run the training script on the latest tub by passing the path to that tub as an argument. You can optionally pass path masks, such as ./data/* or ./data/tub_?_17-08-28 to gather multiple tubs. For example:
<pre>
python ~/mycar/manage.py train --tub <tub folder names comma separated> --model ./models/mypilot.h5
</pre>
:[[File:DonkeyCar_for_Jetson_Nano_7-1.png|400px]]
: It will cost a long time to train a model, please be patient.
: After training, you can get a model, you need to copy the module to your raspberry Pi and test it.
<pre>
rsync -rv --show-progress --partial ~/mycar/models/ pi@<your_ip_address>:~/mycar/models/
</pre>