Flip an image or a set of heatmaps left-right Arguments: tensor {numpy.array or torch.tensor} -- [the input image or heatmaps] Keywo

add new dimensions at the front and the tail

Download a dataset. Args: save_path : str A directory to save the data to. dataset : str, o

3x3 convolution with padding

Deprecated, please use get_landmarks_from_image Arguments: image_or_path {string or numpy.array or torch.tensor} -- The input

Generate and affine transformation matrix. Given a set of points, a center, a scale and a targer resolution, the function generates and affin

sum over the first and last dimention

appdata_dir(appname=None, roaming=False) Get the path to the application directory, where applications are allowed to write user specific fi

Detects faces in a given image. This function detects the faces present in a provided BGR(usually) image. The input can be either

Execute an replication callback `__data_parallel_replicate__` on each module created by original replication. The callback will be invoked w

Predict the landmarks for each face present in the image. This function predicts a set of 68 2D or 3D images, one for each image present.

Obtain (x,y) coordinates given a set of N heatmaps. If the center and the scale is provided the function will return the points also in the or

Convert path (represented as a string) or torch.tensor to a numpy.ndarray Arguments: tensor_or_path {numpy.ndarray, torch.tens

Args: master_callback: a callback to be invoked after having collected messages from slave devices.

Compute the mean and standard-deviation with sum and square-sum. This method also maintains the moving average on the master device.

Traverse the input module and its child recursively and replace all instance of torch.nn.modules.batchnorm.BatchNorm*N*d to Synchronized

Center crops an image or set of heatmaps Arguments: image {numpy.array} -- an rgb image center {numpy.array} -- the center of the

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor):

Detects faces from all the images present in a given directory. Arguments: path {string} -- a string containing a path that po

Affine inverse deformation ### Params: * image - ndarray: original image * p - ndarray: an array with size [n, 2], original co

Affine inverse deformation ### Params: * image - ndarray: original image * p - ndarray: an array with size [n, 2], original co

Register an slave device. Args: identifier: an identifier, usually is the device id. Returns: a `SlavePipe` obj