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.

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

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

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.

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

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

Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two boxes box1 and box2 is defined as

Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two masks, mask1 and mask2 is defined as

Computes pairwise intersection-over-union between box and mask collections. Args: box_mask_list1: BoxMaskList holding N boxes and masks

Computes pairwise intersection-over-union between box collections. Args: boxes1: a numpy array with shape [N, 4] holding N boxes. box

Computes pairwise intersection-over-union between box collections. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding

Computes pairwise intersection-over-union between mask collections. Args: masks1: a numpy array with shape [N, height, width] holding N mas

Determine if a checkpoint should be saved on current epoch. Args: cfg (CfgNode): configs to save. cur_epoch (int): current nu

Determine if a checkpoint should be saved on current epoch. Args: cfg (CfgNode): configs to save. cur_epoch (int): current nu

Determine if the model should be evaluated at the current epoch. Args: cfg (CfgNode): configs. Details can be found in sl

Determines if the current process is the master process.

Determines if the current process is the root process.

Start to record time.

Start to record time.

Start to record time.

Stop to record time.

Stop to record time.

Stop to record time.

Perform AlexNet-style PCA jitter on the given image. Args: image (array): list of images to perform lighting jitter. alphastd

Perform AlexNet-style PCA jitter on the given images. Args: images (tensor): images to perform lighting jitter. Dimension is

Perform AlexNet-style PCA jitter on the given list of images. Args: images (list): list of images to perform lighting jitter.

Loading boxes and labels from csv files. Args: cfg (CfgNode): config. mode (str): 'train', 'val', or 'test' mode. Return

Load image paths and labels from a "frame list". Each line of the frame list contains: `original_vido_id video_id frame_id path labels`

Loading image paths from corresponding files. Args: cfg (CfgNode): config. is_train (bool): if it is training dataset or not

Loading checkpoint logic for testing.

Loading checkpoint logic for testing.

Loading checkpoint logic for training.

Loading checkpoint logic for training.

Create init function passed to pytorch data loader. Args: dataset (torch.utils.data.Dataset): the given dataset.

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

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

Log the stats. Args: cur_iter (int): the current iteration of testing.

log the stats of the current iteration. Args: cur_epoch (int): the number of current epoch. cur_iter (int): t

log the stats of the current iteration. Args: cur_epoch (int): the number of current epoch. cur_iter (int): t

Logs json stats. Args: stats (dict): a dictionary of statistical information to log.

Log info, includes number of parameters, gpu usage, gflops and activation count. The model info is computed when the model is in validati

Retrieve the learning rate to specified values at specified epoch with the cosine learning rate schedule. Details can be found in: Ilya L

Retrieve the learning rate to specified values at specified epoch with the steps with relative learning rate schedule. Args: cfg

Creates the checkpoint directory (if not present already). Args: path_to_job (string): the path to the folder of the current job.

Creates the checkpoint directory (if not present already). Args: path_to_job (string): the path to the folder of the current job.

Multi-class version of non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have h

Multi-class version of non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have h

Collate function for repeated augmentation. Each instance in the batch has more than one sample. Args: batch (tuple or list): dat

Returns: (int): the number of videos in the dataset.

Returns: (int): the number of videos in the dataset.

Returns: (int): the number of videos in the dataset.

Returns: (int): the number of clips in total in the dataset.

Returns: (int): the number of videos in the dataset.

Returns: (int): the number of videos in the dataset.

A function to create a colored and labeled confusion matrix matplotlib figure given true labels and preds. Args: cmtx (ndarray):

Plot the input tensor with the optional bounding box and save it to disk. Args: tensor (tensor): a tensor with shape of `NxCxHxW`.

Plot histogram of top-k value from the given array. Args: tag (str): histogram title. array (tensor): a tensor to draw top k