Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

Converts the given value to its unsigned representation.

Cleanup function to ensure Dynamixels are disconnected properly.

Arguments: x: Tensor, shape ``[seq_len, batch_size, embedding_dim]``

qpos: batch, qpos_dim image: batch, num_cam, channel, height, width env_state: None actions: batch, seq, action_dim

qpos: batch, qpos_dim image: batch, num_cam, channel, height, width env_state: None actions: batch, seq, action_dim

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

Sets the state of the environment at the start of each episode.

Sets the state of the environment at the start of each episode.

Sets the state of the environment at the start of each episode.

Sets the state of the environment at the start of each episode.

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spati

Function to plot specific fields from training log(s). Plots both training and test results. :: Inputs - logs = list containing Path objects

Returns the current positions and velocities.

Returns the current positions and velocities.

Returns the current positions and velocities.

Args: input_dict (dict): all the values will be reduced average (bool): whether to do average or sum Reduce the values in the

Warning: does not synchronize the deque!