


This command may be run from ~/mycar dir.This command allows you to plot steering and throttle against predictions coming from a trained model. scale will cause ouput image to be scaled by this amount.optional -start and/or -end can specify a range of frame numbers to use.optional -salient will overlay a visualization of which pixels excited the NN the most.model_type may optionally give a hint about what model type we are loading.
Car localizer movie#
Optional model argument will load the keras model and display prediction as lines on the movie.Optional argument to specify a different config.py other than default: config.py.Uses the image records from -tub dir path given.This command allows you to create a movie file from the images in a Tub. Note: The createcar command still creates a train.py file for backward compatibility, but it's not required for training.To do so, you set CREATE_TENSOR_RT = True. Also Tensorrt models can now be generated. This can be suppressed by setting CREATE_TF_LITE = False in your config. In addition, a Tflite model is automatically generated in training. In version 4.3.0 and later all 3.x models are supported again:ĭonkey train -tub=.Only uses records with positive throttle in training. Supports filtering of records using a function defined in the variable.Allows to continue training a model given by -transfer.Note: There was a regression in version 4.2 where you only had to provide the model name in the model argument, like -model mypilot.h5. Saves the model into path provided by -model.Uses the config file from the -config path (optionally).You may specify more than one tub using a comma separated list -tub=foo/data,bar/data or just leaving spaces like -tub foo/data bar/data. Uses the data from the -tub datastore.There is more detail in Deep Learning Autopilot. Note: This section only applies to version >= 4.1 Opens the web server to delete bad data.Opens a web server to delete bad data from a tub. Type integer values to specify PWM values and hit enter.Opens the PWM channel specified by -channel.This command allows you to manually enter values to interactively set the PWM values and experiment with how your robot responds. Prints the host computer IP address and the car IP address if found.This command attempts to locate your car on the local network using nmap.

Car localizer update#
This is useful if you have update donkeycar and you want those changes reflected in you mycar folder but you don't want to have to recreate your myconfig.py.
Car localizer install#
The donkey command is created when you install the donkeycar Python package.
