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

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

Returns: (int): the number of clips per replica in the IterableDataset.

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.

Read and return the required number of frames for 1 clip. Returns: was_read (bool): False if not enough frames to return.

Retrieves the next clip from the dataset.

Create text labels. Args: classes (list[int]): a list of class ids for each example. scores (list[float] or None): list of sc

Return a clip corresponding to a keyframe index for visualization. Args: keyframe_idx (int): keyframe index.

Return a layer (nn.Module Object) given a hierarchical layer name, separated by /. Args: layer_name (str): the name of th

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

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

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

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

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

Add input to tensorboard SummaryWriter as a video. Args: vid_tensor (tensor): shape of (B, T, C, H, W). Values should lie

Recursively find all SubBN modules and aggregate sub-BN stats. Args: module (nn.Module) Returns: count (int): number of S

All gathers the provided tensors from all processes across machines. Args: tensors (list): tensors to perform all gather across all p

Run all_gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object group: a torch proces

All reduce the provided tensors from all processes across machines. Args: tensors (list): tensors to perform all reduce across all pr

Computes area of masks. Args: box_mask_list: np_box_mask_list.BoxMaskList holding N boxes and masks Returns: a numpy array with

Construct binary label vector given a list of label indices. Args: labels (list): The input label list. num_classes (int): Nu

Calculate the average epoch time among the recorded epochs.

Perform backwarding, gathering the gradients across different process/ GPU group.

Benchmark the speed of data loading in PySlowFast. Args: cfg (CfgNode): configs. Details can be found in slowfast/config

Change coordinate frame of the boxlist to be relative to window's frame. Given a window of the form [ymin, xmin, ymax, xmax], changes boundin

Determine whether the loss is NaN (not a number). Args: loss (loss): loss to check whether is NaN.

Clean up open video files and windows.

Clean up open video files and windows.

Clears the state to prepare for a fresh evaluation.

Clip an array of boxes to an image with the given height and width. Args: boxes (ndarray): bounding boxes to perform clipping.

Clip the boxes with the height and width of the image size. Args: boxes (ndarray): bounding boxes to peform crop. The dimension is

Clip bounding boxes to a window. This op clips input bounding boxes (represented by bounding box corners) to a window, optionally filtering o

Perfrom a color jittering on the input images. The channels of images should be in order BGR. Args: images (tensor): images to pe

Perform color jitter on the given image. Args: image (array): image to perform color jitter. img_brightness (float): jitter r

Perform color jitter on the list of images. Args: images (list): list of images to perform color jitter. img_brightness (floa

Perform color nomration on the given images. Args: images (tensor): images to perform color normalization. Dimension is `

Perform color normalization on the image with the given mean and stddev. Args: image (array): image to perform color normalization.

Compute and update the batch norm stats to make it more precise. During training both bn stats and the weight are changing after every iterat

Compute Average Precision according to the definition in VOCdevkit. Precision is modified to ensure that it does not decrease as recall decre

Compute CorLoc according to the definition in the following paper. https://www.robots.ox.ac.uk/~vgg/rg/papers/deselaers-eccv10.pdf Returns n

Compute precision and recall. Args: scores: A float numpy array representing detection score labels: A boolean numpy array representi

Concatenate list of box_mask_lists. This op concatenates a list of input box_mask_lists into a larger box_mask_list. It also handles con

Constructs the data loader for the given dataset. Args: cfg (CfgNode): configs. Details can be found in slowfast/config/d

Construct a stochastic gradient descent or ADAM optimizer with momentum. Details can be found in: Herbert Robbins, and Sutton Monro. "A s

Construct a stochastic gradient descent or ADAM optimizer with momentum. Details can be found in: Herbert Robbins, and Sutton Monro. "A s

Construct a stochastic gradient descent or ADAM optimizer with momentum. Details can be found in: Herbert Robbins, and Sutton Monro. "A s

Convert the caffe2_layer_name to pytorch format by apply the list of regular expressions. Args: caffe2_layer_name

Aggregate annotations from all frames of a video to form video-level labels. Args: labels (list): The input label list. Returns:

Compute the system memory (RAM) usage for the current device (GB). Returns: usage (float): used memory (GB). total (float): t

Reads a label map and returns a category index. Args: label_map_path: Path to `StringIntLabelMap` proto text file. Returns: A ca

Creates a category index with a single `object` class.

Create sampler for the given dataset. Args: dataset (torch.utils.data.Dataset): the given dataset. shuffle (bool): set to ``T

Decode the video and perform temporal sampling. Args: container (container): pyav container. sampling_rate (int): frame sampl

Collate function for detection task. Concatanate bboxes, labels and metadata from different samples in the first dimension instead of sta

Either display a single frame (BGR image) to a window or write to an output file if output path is provided. Args:

Add the visualized task to the write queue for display/write to outputfile. Args: task (TaskInfo object): task object tha

Either display a single frame (BGR image) to a window or write to an output file if output path is provided.

Scale clip frames from [0, 255] to [0, 1]. Args: x (Tensor): A tensor of the clip's RGB frames with shape: (channel, time

Start to record time.

Stop to record time.

Compute evaluation result. Returns: A dictionary of metrics with the following fields - 1. summary_metrics:

Compute evaluation result. Returns: A named tuple with the following fields - average_precision: float numpy array of a