Round width of filters based on width multiplier Args: width (int): the channel dimensions of the input. mult

Seriialize the tensor to ByteTensor. Note that only `gloo` and `nccl` backend is supported. Args: data (data): data to be ser

Suppresses printing from the current process.

Update grouth truth statitistics. 1. Difficult boxes are ignored when counting the number of ground truth instances as done in Pascal VOC dev

Checks if a label map is valid. Args: label_map: StringIntLabelMap to validate. Raises: ValueError: if label map is invalid.

Join a list of label list. Args: labels (list): The input label list. Returns: labels (list): The joint list of all lists

Synchronize running_mean, and running_var. Call this before eval.

Computes area of boxes. Args: boxlist: BoxList holding N boxes Returns: a numpy array with shape [N*1] representing box areas

Perform color brightness on the given image. Args: var (float): variance. image (array): image to perform color brightness.

Perfrom brightness jittering on the input images. The channels of images should be in order BGR. Args: var (float): jitter ratio

Perform color brightness on the given list of images. Args: var (float): variance. images (list): list of images to perform c

Build a dataset, defined by `dataset_name`. Args: dataset_name (str): the name of the dataset to be constructed. cfg (CfgNode

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

Convert BN parameters to Sub-BN parameters if model contains Sub-BNs. Args: key (OrderedDict): source dict of parameters. mdo

Update the stats in bn layers by calculate the precise stats. Args: loader (loader): data loader to provide training data. mo

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

Evaluates detections as being tp, fp or ignored from a single image. The evaluation is done in two stages: 1. All detections are matched to

Concatenate list of BoxLists. This op concatenates a list of input BoxLists into a larger BoxList. It also handles concatenation of BoxList fiel

Perform color contrast on the given image. Args: var (float): variance. image (array): image to perform color contrast. R

Perfrom contrast jittering on the input images. The channels of images should be in order BGR. Args: var (float): jitter ratio fo

Perform color contrast on the given list of images. Args: var (float): variance. images (list): list of images to perform col

Loads label map proto and returns categories list compatible with eval. This function loads a label map and returns a list of dicts, each of which

Creates dictionary of COCO compatible categories keyed by category id. Args: categories: a list of dicts, each of which has the following keys:

Crop the boxes given the offsets. Args: boxes (array): boxes to crop. x_offset (int): offset on x. y_offset (int): of

Start to record time.

Stop to record time.

Horizontally flip the boxes. Args: boxes (array): box to flip. im_width (int): width of the image. Returns: boxes

Perform forwarding, gathering the stats across different process/ GPU group.

Get a copy of the default config.

Get corner coordinates of boxes. Returns: a list of 4 1-d numpy arrays [y_min, x_min, y_max, x_max]

Given a schedule and epoch index, return the long cycle base shape. Args: schedule (configs): configs that contains training and mult

Calculate the global mean value.

Calculate the Intersection over Union (IoU) of two bounding boxes. Parameters ---------- bb1 : dict Keys: {'x1', 'x2', 'y1',

Retrieve the logger with the specified name or, if name is None, return a logger which is the root logger of the hierarchy. Args:

Based on multigrid hyperparameters, define the schedule of a long cycle. Args: cfg (configs): configs that contains train

Get the function to convert Caffe2 layer names to PyTorch layer names. Returns: (func): function to convert parameter name from Caffe

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

Get parameters for ``crop`` for a random sized crop. Args: img (PIL Image): Image to be cropped. scale (tuple): range

Get the full path to a checkpoint file. Args: path_to_job (string): the path to the folder of the current job. epoch (int): t

Get the rank of the current process.

Retrieves the stem module by name.

Retrieves the lr step index for the given epoch. Args: cfg (CfgNode): configs. Details can be found in slowfast/config/de

Retrieves the transformation module by name.

Get the size of the world.

Compute the GPU memory usage for the current device (GB).

Inflate 2D model weights in state_dict_2d to the 3D model weights in state_dict_3d. The details can be found in: Joao Carreira, and Andre

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

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

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

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

Given the arguemnts, load and initialize the configs. Args: args (argument): arguments includes `shard_id`, `num_shards`,

Main function to spawn the train and test process.

Calculate the median epoch time among the recorded epochs.

Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over

Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over

Convert BN parameters to Sub-BN parameters if model contains Sub-BNs. Args: checkpoint_sd (OrderedDict): source dict of parameters.

bboxes for groundtruth are in [x1,y1,w,h]

bboxes for preds are in format [x1,y1,x2,y2]

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

Pad the given image with the size of pad_size. Args: image (array): image to pad. pad_size (int): size to pad. order

Compute the number of parameters. Args: model (model): model to count the number of parameters.

Parse the following arguments for a default parser for PySlowFast users. Args: shard_id (int): shard id for the current machine. Star

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

Log schedule.

Reads a CSV file of excluded timestamps. Args: exclusions_file: A file object containing a csv of video-id,timestamp. Returns: A s

Read label map and class ids.

AVA evaluation main logic.

Perform color saturation on the given image. Args: var (float): variance. image (array): image to perform color saturation.

Perfrom saturation jittering on the input images. The channels of images should be in order BGR. Args: var (float): jitter ratio

Perform color saturation on the list of given images. Args: var (float): variance. images (list): list of images to perform c

Scale box coordinates in x and y dimensions. Args: boxlist: BoxList holding N boxes y_scale: float x_scale: float Returns: boxli

Convert time index (in second) to frame index. 0: 900 30: 901

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

Perform the video training for one epoch. Args: train_loader (loader): video training loader. model (model): the video model

Check if checkpoint_wrapper is imported.

Args: windows: (B*num_windows, window_size, window_size, C) window_size (tuple[int]): Window size H (int): Height of imag

Transpose the dimension from `channel` x `height` x `width` to `height` x `width` x `channel`. Args: image (array): image to

Transpose the dimension from `height` x `width` x `channel` to `channel` x `height` x `width`. Args: image (array): image to

Args: img (PIL Image): Image to be cropped and resized. Returns: PIL Image: Randomly cropped and resized imag

Generate corresponding clips, boxes, labels and metadata for given idx. Args: idx (int): the video index provided by the

overall_iters (int): the overall number of iterations of one epoch. cfg (CfgNode): configs. mode (str): `train`, `val`, or `t

Args: window_size (int): size of the max length of the deque.

Args: window_size (int): size of the max length of the deque.