Run AVA evaluation given annotation/prediction files.

Calculate and log the final ensembled metrics. ks (tuple): list of top-k values for topk_accuracies. For example, ks = (1

Calculate and log the final ensembled metrics. ks (tuple): list of top-k values for topk_accuracies. For example, ks = (1

Set all the bn layers to eval mode. Args: model (model): model to set bn layers to eval mode.

Get the visualized clips if any.

Get the best checkpoint from the checkpointing folder.

Calculate confusion matrix on the provided preds and labels. Args: preds (tensor or lists of tensors): predictions. Each tensor is in

Retrieves the lr for the given epoch (as specified by the lr policy). Args: cfg (config): configs of hyper-parameters of ADAM, includ

Retrieves the lr for the given epoch (as specified by the lr policy). Args: cfg (config): configs of hyper-parameters of ADAM, includ

Retrieves the lr for the given epoch (as specified by the lr policy). Args: cfg (config): configs of hyper-parameters of ADAM, includ

Calculate the global mean value.

Calculate the global mean value.

Getting keyframe indices, boxes and labels in the dataset. Args: boxes_and_labels (list[dict]): a list which maps from video_idx to

Reads a label map and returns a dictionary of label names to id. Args: label_map_path: path to label_map. use_display_name: whether t

Returns: The rank of the current process within the local (per-machine) process group.

Returns: The size of the per-machine process group, i.e. the number of processes per machine.

Retrieve the loss given the loss name. Args (int): loss_name: the name of the loss to use.

Retrieve the learning rate of the current epoch with the option to perform warm up in the beginning of the training stage. Args:

Get maximum index in label map. Args: label_map: a StringIntLabelMapProto Returns: an integer

Get total number of used boxes. Args: keyframe_indices (list): a list of indices of the keyframes. keyframe_boxes_and_labels

When multigrid training uses a fewer number of frames, we randomly increase the sampling rate so that some clips cover the original span.

Given the path to the video, return the pyav video container. Args: path_to_vid (str): path to the video. multi_thread_decode

Calculate the current average value of the deque.

Calculate the current average value of the deque.

Perform horizontal flip on the given images and corresponding boxes. Args: prob (float): probility to flip the images. images

Horizontally flip the image. Args: prob (float): probability to flip. image (array): image to pad. order (str): order

Horizontally flip the list of image and optional boxes. Args: prob (float): probability to flip. image (list): ilist of image

Perform horizontal flip on the given images and corresponding boxes. Args: prob (float): probility to flip the images. images

Initialize variables needed for distributed training.

Initializes the default process group. Args: local_rank (int): the rank on the current local machine. local_world_size (int):

Performs ResNet style weight initialization. Args: fc_init_std (float): the expected standard deviation for fc layer. zero_in

Compute pairwise intersection areas between masks. Args: box_mask_list1: BoxMaskList holding N boxes and masks box_mask_list2: BoxMas

Compute pairwise intersection areas between boxes. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxes Ret