color transfer for [0,1] float32 inputs

1x1 convolution

Creates a logger object and saves all messages to a file. Args: log_path (str): The path to save the log file. Returns:

Run AVA evaluation given numpy arrays.

Helper function for cropping face and extracting landmarks.

Calculate and log the final AVA metrics.

Perform forwarding, gathering the stats across different process/ GPU group.

Description: - Generate a JSON file containing information about the specified datasets' videos and frames. Args: - dataset:

Convert our data format into the data format used in official AVA evaluation.

Get the groundtruth annotations corresponding the "subset" of AVA val set. We define the subset to be the frames such that (second % 4 == 0).

Return a list of the available masks for cli

Return a list of the available masks for cli

Given a schedule and epoch index, return the long cycle base shape. Args: schedule (configs): configs that contains training and mult

Based on multigrid hyperparameters, define the schedule of a long cycle. Args: cfg (configs): configs that contains train

Get the function to convert Caffe2 layer names to PyTorch layer names. Returns: (func): function to convert parameter name from Caffe

Get the rank of the current process.

Retrieves the lr step index for the given epoch. Args: cfg (CfgNode): configs. Details can be found in slowfast/config/de

Get the size of the world.

Compute the GPU memory usage for the current device (GB).

x,y grid coordinates within the ROI of supplied points :param points: points to generate grid coordinates :returns: array of (x, y) coordin

x,y grid coordinates within the ROI of supplied points :param points: points to generate grid coordinates :returns: array of (x, y) coordin

align and crop the face according to the given bbox and landmarks landmark: 5 key points

Inflate 2D model weights in state_dict_2d to the 3D model weights in state_dict_3d. The details can be found in: Joao Carreira, and Andre