Transform for converting output from dict to a tuple following PySlowFast dataset output format.

Transform for converting video frames as a list of tensors. Each tensor corresponding to a unique pathway.

A scalar meter uses a deque to track a series of scaler values with a given window size. It supports calculating the median and average value

Fuses the information from the Fast pathway to the Slow pathway. Given the tensors from Slow pathway and Fast pathway, fuse information from

Measure the AVA train, val, and test stats.

Image to Patch Embedding

Image to Patch Embedding

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Wrapper for PyTorchVideo datasets.

Randomly selects a rectangle region in an image and erases its pixels. 'Random Erasing Data Augmentation' by Zhong et al. See https://

Internal implementation of Pascal object detection metrics.

Action Predictor for action recognition.

Measure training stats.

Measures validation stats.

Visualize action predictions for videos or folder of images with precomputed and ground-truth boxes in AVA format.

Synchronous Action Prediction and Visualization pipeline with AsyncVis.

Asynchronous Action Prediction and Visualization pipeline with AsyncVis.

Apply for video.

Charades video loader. Construct the Charades video loader, then sample clips from the videos. For training and validation, a single clip is

Wrapper around Detectron2 to return the required predicted bounding boxes as a ndarray.

A timer which computes the epoch time.

Gaussian blur augmentation in SimCLR https://arxiv.org/abs/2002.05709

A class used to get weights and activations from specified layers from a Pytorch model.

GradCAM class helps create localization maps using the Grad-CAM method for input videos and overlap the maps over the input videos as heatmap

Apply mixup and/or cutmix for videos at batch level. mixup: Beyond Empirical Risk Minimization (https://arxiv.org/abs/1710.09412) CutMix:

This class defines multigrid training schedule and update cfg accordingly.

Builds Non-local Neural Networks as a generic family of building blocks for capturing long-range dependencies. Non-local Network computes

Image to Patch Embedding

Image to Patch Embedding

Crop the given PIL Image to random size and aspect ratio with random interpolation. A crop of random size (default: of 0.08 to 1.0) of the origina

Residual block.

Squeeze-and-Excitation (SE) block w/ Swish: AvgPool, FC, Swish, FC, Sigmoid.

Extend Sampler to support "short cycle" sampling. See paper "A Multigrid Method for Efficiently Training Video Models", Wu et al., 2019 (

Perform the multi-view ensemble for testing: each video with an unique index will be sampled with multiple clips, and the predictions of the

VideoManager object for getting frames from video source for inference using multithreading for read and write frames.

VideoManager object for getting frames from video source for inference.

WrongPredictionVis class for visualizing video inputs to Tensorboard for instances that the model makes wrong predictions.

AllGatherWithGradient

AVA Dataset

Basic transformation: Tx3x3, 1x3x3, where T is the size of temporal kernel.

Bottleneck transformation: Tx1x1, 1x3x3, 1x1x1, where T is the size of temporal kernel.

Box collection. BoxList represents a list of bounding boxes as numpy array, where each bounding box is represented as a row of 4 numbers,

Naming conventions for BoxLists. Attributes: boxes: bounding box coordinates. classes: classes per bounding box. scores: scores

Convenience wrapper for BoxList with masks. BoxMaskList extends the np_box_list.BoxList to contain masks as well. In particular, its construc

Contrastive Model, currently mainly focused on memory bank and CSC.

Interface for object detection evalution classes. Example usage of the Evaluator: ------------------------------ evaluator = DetectionEva

Naming conventions for storing the output of the detector. Attributes: source_id: source of the original image. key: unique key corre

Gather tensors from all process, supporting backward propagation.

ImageNet dataset.

Names for the input tensors. Holds the standard data field names to use for identifying input tensors. This should be used by the decoder to

Kinetics video loader. Construct the Kinetics video loader, then sample clips from the videos. For training and validation, a single clip is

Model builder for MViTv1 and MViTv2. "MViTv2: Improved Multiscale Vision Transformers for Classification and Detection" Yanghao Li, Chao

MorphMLP

MorphMLP

A class to evaluate detections.

A class to evaluate detections using Open Images V2 metrics. Open Images V2 introduce group_of type of bounding boxes and this metric handles

CSN models using PyTorchVideo model builder.

MViT models using PyTorchVideo model builder.

R(2+1)D models using PyTorchVideo model builder.

ResNet models using PyTorchVideo model builder.

A class to evaluate detections using PASCAL metrics.

A class to evaluate instance masks using PASCAL metrics.

PatchEmbed.

Evaluate detection result of a single image.

ResNet model builder. It builds a ResNet like network backbone without lateral connection (C2D, I3D, Slow). Christoph Feichtenhofer, Hao

ResNe(X)t 3D head. This layer performs a fully-connected projection during training, when the input size is 1x1x1. It performs a convolut

ResNe(X)t 3D stem module. Performs spatiotemporal Convolution, BN, and Relu following by a spatiotemporal pooling.

ResNe(X)t RoI head.

Stage of 3D ResNet. It expects to have one or more tensors as input for single pathway (C2D, I3D, Slow), and multi-pathway (SlowFast) cas

SlowFast model builder for SlowFast network. Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. "SlowFast networks for

Enum class for sort order. Attributes: ascend: ascend order. descend: descend order.