28 open source projects by uber-research

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)

Code for paper "Learning to Reweight Examples for Robust Deep Learning"

A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.

Tool for interactive embeddings visualization

This repo replicates the results Horgan et al obtained in "Distributed Prioritized Experience Replay"

Paired Open-Ended Trailblazer (POET) and Enhanced POET

safemutations

Deep Neuroevolution

[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

UPSNet: A Unified Panoptic Segmentation Network

Sparse Blocks Networks

Code for Go-Explore: a New Approach for Hard-Exploration Problems

Implementations of the algorithms described in Differentiable plasticity: training plastic networks with gradient descent, a research paper from Uber AI Labs.

No description, website, or topics provided.

Using ideas from product quantization for state-of-the-art neural network compression.

No description, website, or topics provided.

The Go programming language. This fork was created for pprof++, a Go profiler with hardware performance monitoring. Read through the link for more detail: https://eng.uber.com/pprof-go-profiler/

No description, website, or topics provided.