sneakerkg

BEVFormer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

CarND-LaneLines-P1

Lane Finding Project for Self-Driving Car ND

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

dmlc-core

A common code-base for Distributed Machine Learning in C++

dmlc-core-random

fiftyone

The open-source tool for building high-quality datasets and computer vision models

fiftyone-examples

Examples of using FiftyOne

flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

learn-to-cluster

Learning to Cluster Faces (CVPR 2019, CVPR 2020)

meshrcnn

code for Mesh R-CNN, ICCV 2019

minpy

Pure NumPy practice with third-party operator integration

mxnet

An efficient, flexible distributed framework for deep learning

NRI

Neural relational inference for interacting systems - pytorch

ogb

Benchmark datasets, data loaders, and evaluators for graph machine learning

Pixel2Mesh

A complete Pixel2Mesh implementation in PyTorch

PointTrack

PointTrack (ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

sgan

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

sneakerkg.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

tensorflow

Open source software library for numerical computation using data flow graphs.

traffic-signs

Classify Traffic Signs.

Trajectron

Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs" by Boris Ivanovic and Marco Pavone.