Generate random colors. To get visually distinct colors, generate them in HSV space then convert to RGB.

A wrapper for Scikit-Image resize(). Scikit-Image generates warnings on every call to resize() if it doesn't receive the right parameters. The

Load and print networks; create schedulers Parameters: opt (Option class) -- stores all the experiment flags; needs to be a subcl

Forward function used in test time. This function wraps <forward> function in no_grad() so we don't save intermediate steps for backprop

Transform input points from world to screen space. Args: transform: ndc transform points: torch tensor of shape (N, V, 3).

Calculate losses, gradients, and update network weights; called in every training iteration

Calculate losses, gradients, and update network weights; called in every training iteration

Args: bid: rot: op_type: kp: [2,], unbatched, for a single brick in this step connections: [?, 2], unbat

Import the module "data/[dataset_name]_dataset.py". In the file, the class called DatasetNameDataset() will be instantiated. It has to be a s

Import the module "models/[model_name]_model.py". In the file, the class called DatasetNameModel() will be instantiated. It has to be a subcl

convert optical flow into color image :param flow_data: :return: color image

.. warnings:: User should call `model.to(rank)` before this function. Args: model: rank: strict: Return

create a single empty directory if it didn't exist Parameters: path (str) -- a single directory path

print current losses on console; also save the losses to the disk Parameters: epoch (int) -- current epoch iters (int

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

:param d: bricks dict :param azims: If given, overwrite dict camera parameters :param elevs: If given, overwrite dict camera parameters

r""" Slices variables into approximately equal chunks and distributes them across given GPUs. Duplicates references to objects that are no

r"""Scatter with support for kwargs dictionary

It's common to have tensors larger than the available data and pad with zeros. This function removes rows that are all zeros. x: [rows, column

Update learning rates for all the networks; called at the end of every epoch

Print warning information about image size(only print once)

heat: batchsize x channels x h x w

heat: batchsize x channels x h x w

L1 regression loss Arguments: regr (batch x max_objects x dim) gt_regr (batch x max_objects x dim) mask (batch x max_ob