Print and save options It will print both current options and default values(if different). It will save options into a text file / [

Recursively update AttrDict d with AttrDict u

r"""Reset the meter values

Constructs a ResNet-50 model.

Recursively find object and return value

Convert 3x4 rotation matrix to 4d quaternion vector This algorithm is based on algorithm described in https://github.com/KieranWynn/pyquatern

Sample all positive class centers in each rank, and random select neg class centers to filling a fixed `num_sample`. total_l

Save softmax weight for each rank on prefix

Multiplies ('scales') a tensor or list of tensors by the scale factor. Returns scaled outputs. If this instance of :class:`GradScal

r"""Set random seeds for everything. Args: seed (int): Random seed. by_rank (bool):

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

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

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

Converts a Tensor array into a numpy image array. Parameters: input_image (tensor) -- the input image tensor array, range(0, 1)

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

r"""Test the functions defined in the models. by default, we will test the training function, the inference function, the visualization functi

Return: face_proj -- torch.tensor, size (B, N, 2), y direction is opposite to v direction Parameters:

Creates a batch of transformation matrices Args: - R: Bx3x3 array of a batch of rotation matrices - t: Bx3x1 array of

Calculates the 3D joint locations from the vertices Parameters ---------- J_regressor : torch.tensor JxV The regressor array tha

visibility of keypoints, based on the normal direction

Write text to stdout (and a file) and optionally flush.

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

Utility function for write summary to log_writer.

image_1: images with size (n, 3, w, h) with value [-1, 1] image_2: images with size (n, 3, w, h) with value [-1, 1]