:param x: shape (N, C, X, Y, Z) :return:

:param images: [B, C, H, W] :param occ_prev: [B, 1, W, H, D] :param azims: [B] :param elevs: [B] :param obj_

:param images: [B, C, H, W] :param occ_prev: [B, 1, W, H, D] :param azims: [B] :param elevs: [B] :param obj_

:param occ: [B, 1, W, H, D] :param theta: [B, 3, 4] :return:

:param emb: B x N x H x W , +1 is the background :param mask_instance: B x N x H x W :param inds: [(num_brick_types) x (max_n

Return traning losses / errors. train.py will print out these errors on console, and save them to a file

Return traning losses / errors. train.py will print out these errors on console, and save them to a file

Return image paths that are used to load current data

Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNo

Return the static method <modify_commandline_options> of the dataset class.

Return the static method <modify_commandline_options> of the model class.

Return a learning rate scheduler Parameters: optimizer -- the optimizer of the network opt (option class) -- stores all

Should be equivalent to get_brick_info for instances of `Brick` Args: brick: grid_size: Returns:

Initialize a network: 1. register CPU/GPU device (with multi-GPU support); 2. initialize the network weights Parameters: net (network)

r"""check if current process is the master

``` x = [ {'foo': 3, 'bar': 1}, {'foo': 4, 'bar': 2}, {'foo': 5, 'bar': 3}, ] ppp.list_of_dicts__to__dict_of_

Load all the networks from the disk. Parameters: epoch (int) -- current epoch; used in he file name '%s_net_%s.pth' % (epoch, nam

Load all the networks from the disk. Parameters: epoch (int) -- current epoch; used in he file name '%s_net_%s.pth' % (epoch, nam

Apply `fctn` to each element in x_or_iterable. This is a generalization of the map function since this will work recursively for iterabl

r"""Apply this function only to the master GPU.

Merge two dicts that may have nested dicts.

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new model-specific options and rewrite default values for existing options. Parameters: parser -- the option parser

Add new model-specific options, and rewrite default values for existing options. Parameters: parser -- original option p

Add new model-specific options and rewrite default values for existing options. Parameters: parser -- the option parser