l5kit.random.random_generator module

class l5kit.random.random_generator.GaussianRandomGenerator(mean: numpy.ndarray, std: numpy.ndarray, random_seed: Optional[int] = 0)

Bases: l5kit.random.random_generator.RandomGenerator

GaussianRandomGenerator draws samples from a normal distribution with specified mean and standard deviation. Note that this gaussian can be multidimensional.

class l5kit.random.random_generator.LambdaRandomGenerator(sampling_function: Callable[[], numpy.ndarray])

Bases: l5kit.random.random_generator.RandomGenerator

LambdaRandomGenerator generates values by calling the supplied function. Note that instead of this you could also just use this supplied function itself.

class l5kit.random.random_generator.RandomGenerator

Bases: abc.ABC

class l5kit.random.random_generator.ReplayRandomGenerator(values: numpy.ndarray)

Bases: l5kit.random.random_generator.RandomGenerator

ReplayRandomGenerator generates values by sequentially returning the values in the supplied array. It does not loop or reset automatically.

class l5kit.random.random_generator.UniformRandomGenerator(low: numpy.ndarray, high: numpy.ndarray)

Bases: l5kit.random.random_generator.RandomGenerator

UniformRandomGenerator draws samples from a uniform distribution over the half-open interval [low, high).