DeepLab2: A TensorFlow Library for Deep Labeling

by   Mark Weber, et al.

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepLab model variants with pretrained checkpoints as well as model training and evaluation code, allowing the community to reproduce and further improve upon the state-of-art systems. To showcase the effectiveness of DeepLab2, our Panoptic-DeepLab employing Axial-SWideRNet as network backbone achieves 68.0 single-scale inference and ImageNet-1K pretrained checkpoints. We hope that publicly sharing our library could facilitate future research on dense pixel labeling tasks and envision new applications of this technology. Code is made publicly available at <>.


page 2

page 3


EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy

EagerPy is a Python framework that lets you write code that automaticall...

Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

We introduce Larq Compute Engine, the world's fastest Binarized Neural N...

LightSeq: A High Performance Inference Library for Transformers

Transformer, BERT and their variants have achieved great success in natu...

TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank

TensorFlow Ranking is the first open source library for solving large-sc...

Datasets: A Community Library for Natural Language Processing

The scale, variety, and quantity of publicly-available NLP datasets has ...

Horovod: fast and easy distributed deep learning in TensorFlow

Training modern deep learning models requires large amounts of computati...

Tribuo: Machine Learning with Provenance in Java

Machine Learning models are deployed across a wide range of industries, ...