Process the video label for Charades dataset. Use video-level label for training mode, otherwise use clip-level label. Then convert the label

Prunes the boxes in boxlist1 that overlap less than thresh with boxlist2. For each box in boxlist1, we want its IOA to be more than minoverlap wi

Prunes the boxes in list1 that overlap less than thresh with list2. For each mask in box_mask_list1, we want its IOA to be more than minoverlap

Prunes bounding boxes that fall outside a given window. This function prunes bounding boxes that even partially fall outside the given window

Make prediction and put the results in `async_vis` task queue. Args: task (TaskInfo object): task object that contain

Grabbing frames from VideoCapture.

Perform random spatial crop on the given images and corresponding boxes. Args: images (tensor): images to perform random crop. The di

Perform random crop on a list of images. Args: images (list): list of images to perform random crop. size (int): size to crop

Crop the given images to random size and aspect ratio. A crop of random size (default: of 0.08 to 1.0) of the original size and a random aspe

This is similar to random_resized_crop. However, it samples two different boxes (for cropping) for the first and last frame. It then linearly

Perform ResNet style random scale jittering: randomly select the scale from [1/max_size, 1/min_size]. Args: image (array): im

Perform ResNet style random scale jittering on a list of image: randomly select the scale from [1/max_size, 1/min_size]. Note that all th

Perform a spatial short scale jittering on the given images and corresponding boxes. Args: images (tensor): images to perform sca

Perform a spatial short scale jittering on the given images and corresponding boxes. Args: images (list): list of images to perfo

Perform random sized cropping on the given image. Random crop with size 8% - 100% image area and aspect ratio in [3/4, 4/3]. Args:

Performs Inception-style cropping (used for training).

Perform random sized cropping on the given list of images. Random crop with size 8% - 100% image area and aspect ratio in [3/4, 4/3].

Reset the deque.

Reset the Meter.

Reset the Meter.

Reset the epoch timer.

How many results are ready to be returned.

This function is to load images with support of retrying for failed load. Args: image_paths (list): paths of images needed to be loa

Revert scaled input boxes to match the original image size. Args: size (int): size of the cropped image. boxes (array): shape

Revert normalization for a given tensor by multiplying by the std and adding the mean. Args: tensor (tensor): tensor to revert normal

Convert clip frames from RGB mode to BRG mode. Args: x (Tensor): A tensor of the clip's RGB frames with shape: (channel,

Runs a function from a child process. Args: local_rank (int): rank of the current process on the current machine. num_proc (i

Run prediction asynchronously.

Run visualization asynchronously.

Returns: (torch.utils.data.Sampler): video sampler for the dataset.

Save a checkpoint. Args: model (model): model to save the weight to the checkpoint. optimizer (optim): optimizer to save the

Save a checkpoint. Args: model (model): model to save the weight to the checkpoint. optimizer (optim): optimizer to save the

Sets the optimizer lr to the specified value. Args: optimizer (optim): the optimizer using to optimize the current network. n

Sets up the logging for multiple processes. Only enable the logging for the master process, and suppress logging for the non-master processes

" Shuffles the data. Args: loader (loader): data loader to perform shuffle. cur_epoch (int): number of the current epoch.

Perform spatial sampling on the given video frames. If spatial_idx is -1, perform random scale, random crop, and random flip on the given

Perform left, center, or right crop of the given list of images. Args: size (int): size to crop. image (list): ilist of image

Start threads to read and write frames.

Helper function to synchronize (barrier) among all processes when using distributed training

Perform multi-view testing on the pretrained video model. Args: cfg (CfgNode): configs. Details can be found in slowfast/

Computes the top-k accuracy for each k. Args: preds (array): array of predictions. Dimension is N. labels (array): array of l

Computes the top-k error for each k. Args: preds (array): array of predictions. Dimension is N. labels (array): array of labe

Train a video model for many epochs on train set and evaluate it on val set. Args: cfg (CfgNode): configs. Details can be found in

Perform uniform spatial sampling on the images and corresponding boxes. Args: images (tensor): images to perform uniform crop. The di

Collect the predictions from the current batch and perform on-the-flight summation as ensemble. Args: preds (tens

Update the current stats. Args: top1_err (float): top1 error rate. top5_err (float): top5 error rate.

Update the current stats. Args: top1_err (float): top1 error rate. top5_err (float): top5 error rate.

Perform layer weights and activations visualization on the model. Args: cfg (CfgNode): configs. Details can be found in s

Return class ids that the model predicted incorrectly.