Get values according to the filepath from one lmdb named client_key. Args: filepath (str | obj:`Path`): Here, filepath is the lmd

Get environment information. Currently, only log the software version.

Get environment information. Currently, only log the software version.

Get 68 densemarks for cropped images. Should only have one face at most in the cropped image.

Get 68 densemarks for cropped images. Should only have one face at most in the cropped image.

batch tensors transpose. :param tensors: Tensor[(ROW*COL)*D1*...], or Iterable of same size tensors. :param original_nrow: original ROW

batch tensors transpose. :param tensors: Tensor[(ROW*COL)*D1*...], or Iterable of same size tensors. :param original_nrow: original ROW

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

imresize function same as MATLAB. It now only supports bicubic. The same scale applies for both height and width. Args: img (Ten

imresize function same as MATLAB. It now only supports bicubic. The same scale applies for both height and width. Args: img (Ten

Initialize the dlib detectors and predictors.

Initialize the dlib detectors and predictors.

We now only use wandb to sync tensorboard log.

We now only use wandb to sync tensorboard log.

Load image and return as a NumPy array.

Load image and return as a NumPy array.

Load image and convert to PyTorch tensor with shape (1, C, H, W).

Load image and convert to PyTorch tensor with shape (1, C, H, W).

Make dirs for experiments.

Make dirs for experiments.

Register the given object under the the name `obj.__name__`. Can be used as either a decorator or not. See docstring of this

Register the given object under the the name `obj.__name__`. Can be used as either a decorator or not. See docstring of this

Convert a RGB image to YCbCr image. This function produces the same results as Matlab's `rgb2ycbcr` function. It implements the ITU-R BT.601

Convert a RGB image to YCbCr image. This function produces the same results as Matlab's `rgb2ycbcr` function. It implements the ITU-R BT.601

Scan a directory to find the interested files. Args: dir_path (str): Path of the directory. keywords (str | tuple(str), optional)

Scan a directory to find the interested files. Args: dir_path (str): Path of the directory. keywords (str | tuple(str), optional)

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

Get affine matrix, warp and cropped faces. Also get inverse affine matrix for post-processing.

Get affine matrix, warp and cropped faces. Also get inverse affine matrix for post-processing.

Convert a YCbCr image to BGR image. The bgr version of ycbcr2rgb. It implements the ITU-R BT.601 conversion for standard-definition telev

Convert a YCbCr image to BGR image. The bgr version of ycbcr2rgb. It implements the ITU-R BT.601 conversion for standard-definition telev

Convert a YCbCr image to RGB image. This function produces the same results as Matlab's ycbcr2rgb function. It implements the ITU-R BT.601 co

Convert a YCbCr image to RGB image. This function produces the same results as Matlab's ycbcr2rgb function. It implements the ITU-R BT.601 co