Apply mask to supplied image :param img: max 3 channel image :param mask: [0-255] values in mask :returns: new image with mask applied

Apply mask to supplied image :param img: max 3 channel image :param mask: [0-255] values in mask :returns: new image with mask applied

Collects image and label lists. Args: dataset_name (str): A list containing one dataset information. e.g., 'FF-F2F' Retu

3x3 convolution with padding

3x3 convolution with padding

3x3 convolution with padding

Expand original boundingbox by scale. :param bbx: original boundingbox :param width: frame width :param height: frame height

Computes the focal loss

Get a copy of the default config.

Get the last checkpoint from the checkpointing folder. Args: path_to_job (string): the path to the folder of the current job.

Given the configs, retrieve the specified lr policy function. Args: lr_policy (string): the learning rate policy to use for the job.

Compute mAP for multi-label case. Args: preds (numpy tensor): num_examples x num_classes. labels (numpy tensor): num_examples

Compute statistics for the current model given the config. Args: model (model): model to perform analysis. cfg (CfgNode): con

Get the full path to a checkpoint file. Args: path_to_job (string): the path to the folder of the current job. epoch (int): t

Retrieves the transformation module by name.

Determines if the given directory contains a checkpoint. Args: path_to_job (string): the path to the folder of the current job.

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

Matches the colour distribution of the target image to that of the source image using a linear transform. Images are expected to be of fo

Matches the colour distribution of the target image to that of the source image using a linear transform. Images are expected to be of

Compute the batched mahalanobis distance. values is a batch of feature vectors. mean is either the mean of the distribution to compare, or

Returns a unique identifier for a video id & timestamp.

Reads a CSV file of excluded timestamps. Args: exclusions_file: A file object containing a csv of video-id,timestamp. Returns: A s

Read label map and class ids.

Transfers the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.

Transfers the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.

AVA evaluation main logic.

Convert the Sub-BN paprameters to normal BN parameters in a state dict. There are two copies of BN layers in a Sub-BN implementation: `bn.bn`

Given the predictions, labels, and a list of top-k values, compute the number of correct predictions for each top-k value. Args:

Estimate N-D similarity transformation with or without scaling. Parameters ---------- src : (M, N) array Source coordinates.

Write prediction results into official formats.

Constructs a ir-101 model.

Constructs a ir-18 model.

Constructs a ir-34 model.

Constructs a ir-50 model.

Constructs a ir_se-50 model.