Loop through the registered actions and fire all callbacks Args: hook The name of the hook to check, defaults to all

save the metrics to the logging dictionary arguments: log_dict (Dict) -- metrics/media to be logged in current step

Creates a specified YOLOv5 model Arguments: name (str): name of model, i.e. 'yolov5s' pretrained (bool): load pretrained weights

Set weight decay and step optimizer.

Make `p` listy and the same length as `q`.

Method to check if there is a vehicle in front of the agent blocking its path. :param vehicle_list (list of carla.Vehicle): list

Changes the target speed :param speed: new target speed in Km/h :return:

Clear optimizer gradients.

:param pts_lidar: (N, 3) :return pts_rect: (N, 3)

Args: data_dict: points: optional, (N, 3 + C_in) gt_boxes: optional, (N, 7 + C) [x, y, z, dx, dy,

Set `val` inside the optimizer dictionary at `key`.

Convert a carla transform to transform type. Considers the conversion from left-handed system (unreal) to right-handed system. Consid

Compute speed of a vehicle in Km/h. :param vehicle: the vehicle for which speed is calculated :return: speed as a float in Km/h

:param pts_lidar: (N, 3) :return pts_rect: (N, 3)

Args: batch_dict: batch_size: batch_cls_preds: (B, num_boxes, num_classes | 1) or (N1+N2+..., num

rotated box iou running in gpu. 500x faster than cpu version (take 5ms in one example with numba.cuda code). convert from [this project](

Args: code_weights: (#codes) float list if not None. Code-wise weights.

Creates matrix from carla transform.

Read a hyperparameter `key` in the optimizer dictionary.

:param pts_lidar: (N, 3) :return pts_rect: (N, 3)