Reset the Meter.

Convenience function for accesssing box coordinates. Returns: a numpy array of shape [N, 4] representing box corners

Return visualized frames/clips in the correct order based on task id if result(s) is available. Otherwise, raise queue.Empty exceptio

Accesses data associated with the specified field in the box collection. Args: field: a string parameter used to speficy a related

Return number of boxes held in collections.

Add data to a specified field. Args: field: a string parameter used to speficy a related field to be accessed. field_data

Convenience function for accessing masks. Returns: a numpy array of shape [N, height, width] representing masks

Add the new task to task queue. Args: task (TaskInfo object): task object that contain the necessary info

Args: cfg (CfgNode): model building configs, details are in the comments of the config file. Returns: nn.Module:

Gather boxes from BoxList according to indices and return new BoxList. By default, gather returns boxes corresponding to the input index list, as

Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id u

Add a new scalar value to the deque.

Builds the video model. Args: cfg (configs): configs that contains the hyper-parameters to build the backbone. Details can be

Return the actual head activation function given the activation fucntion name. Args: act_func (string): activation function to use.

Calculate the current median value of the deque.

Start to record time.

Update the current stats. Args: preds (tensor): prediction embedding. ori_boxes (tensor): original boxes (x1,

The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi

With 50% prob, negate the value

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

Return all non-box fields.

Stop to record time.

Load the checkpoint from the given file. If inflation is True, inflate the 2D Conv weights from the checkpoint to 3D Conv. Args:

Load the checkpoint from the given file. If inflation is True, inflate the 2D Conv weights from the checkpoint to 3D Conv. Args:

Scale the short side of the image to size. Args: size (int): size to scale the image. image (array): image to perform short s

The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi

ResBlock class constructs redisual blocks. More details can be found in: Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun.

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

Given scale, ratio, height and width, return sampled coordinates of the videos.

Add multiple scalars to Tensorboard logs. Args: data_dict (dict): key is a string specifying the tag of value.

Converts a BoxList containing 'masks' into a BoxMaskList. Args: boxlist: An np_box_list.BoxList object. Returns: An np_box_mask_

Gather boxes from np_box_mask_list.BoxMaskList according to indices. By default, gather returns boxes corresponding to the input index list, as

Get path for storing checkpoints. Args: path_to_job (string): the path to the folder of the current job.

Get path for storing checkpoints. Args: path_to_job (string): the path to the folder of the current job.

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

Sample a clip of size clip_size from a video of size video_size and return the indices of the first and last frame of the clip. If clip_idx i

Convert the image to gray scale. Args: image (tensor): image to convert to gray scale. Dimension is `channel` x `height`

Log the stats. Args: cur_epoch (int): the current epoch. cur_iter (int): the current iteration.

The `__init__` method of any subclass should also contain these arguments. Args: dim_in (int): the channel dimension of

Calculate and plot confusion matrix to a SummaryWriter. Args: writer (SummaryWriter): the SummaryWriter to write the matrix to.

Add heatmap to 2D tensor. Args: tensor (tensor): a 2D tensor. Tensor value must be in [0..1] range. Returns: heatmap (ten

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

Computes area of boxes. Args: boxes: Numpy array with shape [N, 4] holding N boxes Returns: a numpy array with shape [N*1] repre

Computes area of masks. Args: masks: Numpy array with shape [N, height, width] holding N masks. Masks values are of type np.uint8 a

Blend two images with a given weight alpha. Args: images1 (tensor): the first images to be blended, the dimension is `num

Draw predicted labels or ground truth classes to clip. Draw bouding boxes to clip if bboxes is provided. Boxes will gradually fade in

Draw predicted labels or ground truth classes to clip. Draw bouding boxes to clip if bboxes is provided. Boxes will gradually fade in

Return the targeted layer (nn.Module Object) given a hierarchical layer name, separated by /. Args: model (model): model to get l

Run 'func' on one or more GPUs, specified in cfg Args: cfg (CfgNode): configs. Details can be found in slowfast/config/de

Parse AVA bounding boxes files. Args: ann_filenames (list of str(s)): a list of AVA bounding boxes annotation files. ann_is_g

Plot confusion matrices and histograms for eval/test set. Args: preds (tensor or list of tensors): list of predictions.

Loads boxes and class labels from a CSV file in the AVA format. CSV file format described at https://research.google.com/ava/download.html. Ar

Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py n_workers (Optional

Choose an x-coordinate from the box to make sure the text label does not go out of frames. By default, the left x-coordinate is

Copies the extra fields of boxlist_to_copy_from to boxlist_to_copy_to. Args: boxlist_to_copy_to: BoxList to which extra fields are copied.

Get color for a class id. Args: class_id (int): class id.

Add correspondding bounding boxes.

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.

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

Clears the state to prepare for a fresh evaluation.

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

Get video randaug transform. Args: input_size: The size of the input video in tuple. auto_augment: Parameters for randaug. A