Inference script for Oasis 500M

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

PyTorch implementation of R-MAE https//arxiv.org/abs/2306.05411

Code release for ConvNeXt V2 model

Code for Point-Level Regin Contrast (https//arxiv.org/abs/2202.04639)

code release of research paper "Exploring Long-Sequence Masked Autoencoders"

PyTorch implementation of Asymmetric Siamese (https://arxiv.org/abs/2204.00613)

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

Grid features pre-training code for visual question answering

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

A flexible, high-performance 3D simulator for Embodied AI research.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

A repository of common methods, datasets, and tasks for video research

Multi-Target Embodied Question Answering

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Non-local Neural Networks for Video Classification

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

Code for Iterative Reasoning Paper (CVPR 2018)

Tensorboard for Caffe2

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

An End-To-End, Lightweight and Flexible Platform for Game Research

Tensorflow Faster RCNN for Object Detection

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation