Add the clip and corresponding id. Args: idx (int): the current index of the clip. frames (list[ndarray]): li

Adds detections for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image.

Calculate the average epoch time among the recorded epochs.

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Perform center crop on input images. Args: size (int): size of the cropped height and width. image (array): the image to perf

This function converts target class indices to one-hot vectors, given the number of classes. Args: targets (loader): Class labels

Peform crop on the bounding boxes given the offsets. Args: boxes (ndarray or None): bounding boxes to peform crop. The dimension

Stochastic Depth per sample.

Evaluates detections and returns a dictionary of metrics.

Run AVA evaluation given numpy arrays.

Filter to keep only boxes and masks with score exceeding a given threshold. This op keeps the collection of boxes and masks whose corresponding s

Filter to keep only boxes with score exceeding a given threshold. This op keeps the collection of boxes whose corresponding scores are greate

Calculate and log the final AVA metrics.

Obtain all activations from layers that we register hooks for. Args: input (tensors, list of tensors): the model input.

Get the best checkpoint from the checkpointing folder.

Get a copy of the default config.

Read json file with entries {classname: index} and return an array of class names in order. If parent_path is provided, load and map all

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

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

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

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 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

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Given the video index, return the list of sampled frame indexes. Args: index (int): the video index. temporal

Get the grayscale for the input images. The channels of images should be in order BGR. Args: images (tensor): the input images fo

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

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

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

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

Compute pairwise intersection areas between boxes. Args: boxes1: a numpy array with shape [N, 4] holding N boxes boxes2: a numpy arra

Compute pairwise intersection areas between masks. Args: masks1: a numpy array with shape [N, height, width] holding N masks. Masks

Get the time for the last epoch.

Loads label map proto. Args: path: path to StringIntLabelMap proto text file. Returns: a StringIntLabelMapProto

Log the stats of the current epoch. Args: cur_epoch (int): the number of current epoch.

Returns a unique identifier for a video id & timestamp.

Prepare output as a list of tensors. Each tensor corresponding to a unique pathway. Args: frames (tensor): frames of images sampl

Replace all `keyframe_sec` in `dictionary` with `keyframe_idx` and merge all [`box_coordinate`, `box_labels`] pairs into [`al

Normalize and prepare inputs as a list of tensors. Each tensor correspond to a unique pathway. Args: frames (list of array): list

RandAugment: Practical automated data augmentation... - https://arxiv.org/abs/1909.13719 Create a RandAugment transform :param config_st

AVA evaluation main logic.

Sort boxes and associated fields according to a scalar field. A common use case is reordering the boxes according to descending scores. Args

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`

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:

Before every epoch, check if long cycle shape should change. If it should, update cfg accordingly. Args: cfg

Write prediction results into official formats.

Args: num_splits (int): number of splits. args (list): other arguments.

Args: dim_in (int): the channel dimensions of the input. ratio (float): the channel reduction ratio for squeeze.

Calculate localization map for all inputs with Grad-CAM. Args: inputs (list of tensor(s)): the input clips. l

Labels true/false positives of detections of an image across all classes. Args: detected_boxes: A float numpy array of shape [N, 4]

Labels boxes detected with the same class from the same image as tp/fp. Args: detected_boxes: A numpy array of shape [N, 4] represe

Constructs the imdb.

Construct the video loader.

Construct the video loader.

Construct the video loader.

Construct the video loader.

Construct the video loader.

Construct the video loader.

Builds a single pathway ResNet model. Args: cfg (CfgNode): model building configs, details are in the co

Builds a SlowFast model. Args: cfg (CfgNode): model building configs, details are in the comments of the

Builds a X3D model. Args: cfg (CfgNode): model building configs, details are in the comments of the conf

Builds a single pathway ResNet model. Args: cfg (CfgNode): model building configs, details are in the co

Builds a single pathway R(2+1)D model. Args: cfg (CfgNode): model building configs, details are in the c

Builds a SlowFast model. The first pathway is the Slow pathway and the second pathway is the Fast pathway. Args:

Builds a single pathway ResNet model. Args: cfg (CfgNode): model building configs, details are in the co

Builds a single pathway X3D model. Args: cfg (CfgNode): model building configs, details are in the comme

Calculate the aggregated mean and stds. Args: means (tensor): mean values. stds (tensor): standard deviations

Return a clip of `num_frames` frames starting from `start_idx`. If not enough frames from `start_idx`, return the remaining frames fr