r"""Evaluating img2img network to obtain pseudo-ground truth images. Args: pseudo_gen (callable): Function converting mask to ima

r"""Return dataset objects for the training and validation sets. Args: cfg (obj): Global configuration file. Returns: (dict)

Return the trainer object. Args: cfg (Config): Loaded config object. net_G (obj): Generator network object. net_D (obj):

r"""Initialize distributed training

r"""Create colors for segmentation label ids. Args: N (int): Number of labels.

r"""Load network weights, optimizer parameters, scheduler parameters from a checkpoint. Args: cfg (obj): Global configura

r""" Build lmdb for training/testing. Usage: python scripts/build_lmdb.py \ --config configs/data_image.yaml \ --data_root /mnt/bi

r"""Create the logging directory Args: logdir (str): Log directory name

r"""Obtaining Minecraft default color. Args: img (H x W x 1 int32 numpy tensor): Segmentation map.

r"""Parse user input arguments

r"""Custom data pre-processing function. Utilize this function if you need to preprocess your data before sending it to the generator and

Recursively update AttrDict d with AttrDict u

r"""Reset the meter values

Recursively find object and return value

r"""Sample camera randomly and precompute everything used by both Gen and Dis. Args: data (dict): images (N x 3 x

r"""Save PIL Image to JPEG. Args: fullname (str): Full save path. output_img (PIL Image): Image to be saved.

r"""Save response content Args: response: destination: Path to save the file. Returns:

r"""Set GPU affinity Args: gpu_id (int): Which gpu device.

r"""Set summary writer Args: log_dir (str): Log directory.

r"""Compute the spectral norm normalized matrix. Args: weight (Parameters): pytorch layer parameter tensor. u (tensor

r"""Reshape weight to obtain the matrix form. Args: weight (Parameters): pytorch layer parameter tensor.

r"""Reshape weight to obtain the matrix form. Args: weight (Parameters): pytorch layer parameter tensor. Returns:

r"""Things to do before an epoch. Args: current_epoch (int): Current number of epoch.

r"""Convert tensor to image. Args: image_tensor (torch.tensor or list of torch.tensor): If tensor then (NxCxHxW) or (NxTxCxHx

r"""Convert a 3 dimensional torch tensor to a PIL image with the desired width and height. Args: image (3 x W1 x H1 tensor): Image te

r"""Move all data to ``channels_last`` format. Args: data (dict, list or tensor): Input data.

r"""Move all tensors inside data to gpu. Args: data (dict, list, or tensor): Input data.

r"""Move all halfs to float. Args: data (dict, list or tensor): Input data.

r"""Update the moving average.

r"""Wrap the networks and the optimizers with AMP DDP and (optionally) model average. Args: cfg (obj): Global configuration.

r"""Dump binary contents of file associated with key to LMDB. Args: txn: handle to LMDB. key (str): LMDB key for this filepath.

r"""Write the value in the tensorboard. Args: img_grid: step (int): Epoch or iteration number.

Utility function for write summary to log_writer.

r""" Args: seg_map (tensor): Input Segmentation maps to be colorized.

r"""Initializes augmentation pipeline. Args: aug_list (list): List of augmentation operations in sequence. individual

r"""GAN loss constructor. Args: target_real_label (float): Desired output label for the real images. target_fake_labe