Same-category comparison
Name	Rank	Metrics
webis-de/small-text	15,565	Language: Python Stars: 647 Forks: 78 Description: Active Learning for Text Classification in Python.
BlackHC/tfpyth	15,567	Language: Python Stars: 646 Forks: 95 Description: Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).
SJTUjinmao/ArkEval	15,568	Language: Python Stars: 646 Forks: 16 Description: ArkEval: Benchmarking and Evaluating Automated Code Repair for ArkTS.
maciejkula/rustlearn	15,572	Language: Rust Stars: 646 Forks: 55 Description: Machine learning crate for Rust.
AnyLoc/AnyLoc	15,577	Language: Python Stars: 645 Forks: 66 Description: AnyLoc: Universal Visual Place Recognition (RA-L 2023).
erdogant/bnlearn	15,583	Language: Jupyter Notebook Stars: 645 Forks: 61 Description: Python package for Causal Discovery by learning the graphical structure of Bayesian networks. Structure Learning, Parameter Learning, Inferences, Sampling methods.
huanghoujing/AlignedReID-Re-Production-Pytorch	15,584	Language: Python Stars: 645 Forks: 189 Description: Reproduce AlignedReID: Surpassing Human-Level Performance in Person Re-Identification, using Pytorch.
jvanvugt/pytorch-domain-adaptation	15,586	Language: Python Stars: 645 Forks: 107 Description: A collection of implementations of adversarial domain adaptation algorithms.

Name

Rank

Metrics

15,565

Language:: Python
Stars:: 647
Forks:: 78
Description:: Active Learning for Text Classification in Python.

BlackHC/tfpyth

15,567

Language:: Python
Stars:: 646
Forks:: 95
Description:: Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).

SJTUjinmao/ArkEval

15,568

Language:: Python
Stars:: 646
Forks:: 16
Description:: ArkEval: Benchmarking and Evaluating Automated Code Repair for ArkTS.

maciejkula/rustlearn

15,572

Language:: Rust
Stars:: 646
Forks:: 55
Description:: Machine learning crate for Rust.

AnyLoc/AnyLoc

15,577

Language:: Python
Stars:: 645
Forks:: 66
Description:: AnyLoc: Universal Visual Place Recognition (RA-L 2023).

erdogant/bnlearn

15,583

Language:: Jupyter Notebook
Stars:: 645
Forks:: 61
Description:: Python package for Causal Discovery by learning the graphical structure of Bayesian networks. Structure Learning, Parameter Learning, Inferences, Sampling methods.

huanghoujing/AlignedReID-Re-Production-Pytorch

15,584

Language:: Python
Stars:: 645
Forks:: 189
Description:: Reproduce AlignedReID: Surpassing Human-Level Performance in Person Re-Identification, using Pytorch.

jvanvugt/pytorch-domain-adaptation

15,586

Language:: Python
Stars:: 645
Forks:: 107
Description:: A collection of implementations of adversarial domain adaptation algorithms.

Key parameters and specifications
Parameter	Value
Language	Python
Category	Model Development
Subcategory	Architecture
Keywords	Computer vision
Stars	646
Forks	112
Contributors	0
Created date	2019-03-02
Updated date	2026-10-01
Stars in 1 day	0
Stars in 7 days	0
Rank	15,575
Previous rank	15,384
Rank change	-191
7-day stars rank	15,067
Previous 7-day stars rank	15,069
7-day stars rank change	2
Total stars rank	15,853
Previous total stars rank	15,825
Total stars rank change	-28
Country	USA

Parameter

Value

Language

Python

UPSNet: A Unified Panoptic Segmentation Network

Introduction

UPSNet is initially described in a CVPR 2019 oral paper.

Disclaimer

This repository is tested under Python 3.6, PyTorch 0.4.1. And model training is done with 16 GPUs by using horovod. It should also work under Python 2.7 / PyTorch 1.0 and with 4 GPUs.

License

Citing UPSNet

If you find UPSNet is useful in your research, please consider citing:

@inproceedings{xiong19upsnet,
    Author = {Yuwen Xiong, Renjie Liao, Hengshuang Zhao, Rui Hu, Min Bai, Ersin Yumer, Raquel Urtasun},
    Title = {UPSNet: A Unified Panoptic Segmentation Network},
    Conference = {CVPR},
    Year = {2019}
}

Main Results

COCO 2017 (trained on train-2017 set)

	test split	PQ	SQ	RQ	PQTh	PQSt
UPSNet-50	val	42.5	78.0	52.4	48.5	33.4
UPSNet-101-DCN	test-dev	46.6	80.5	56.9	53.2	36.7

Cityscapes

	PQ	SQ	RQ	PQTh	PQSt
UPSNet-50	59.3	79.7	73.0	54.6	62.7
UPSNet-101-COCO (ms test)	61.8	81.3	74.8	57.6	64.8

Requirements: Software

We recommend using Anaconda3 as it already includes many common packages.

Requirements: Hardware

We recommend using 4~16 GPUs with at least 11 GB memory to train our model.

Installation

Clone this repo to $UPSNet_ROOT

Run init.sh to build essential C++/CUDA modules and download pretrained model.

For Cityscapes:

Assuming you already downloaded Cityscapes dataset at $CITYSCAPES_ROOT and TrainIds label images are generated, please create a soft link by ln -s $CITYSCAPES_ROOT data/cityscapes under UPSNet_ROOT, and run init_cityscapes.sh to prepare Cityscapes dataset for UPSNet.

For COCO:

Assuming you already downloaded COCO dataset at $COCO_ROOT and have annotations and images folders under it, please create a soft link by ln -s $COCO_ROOT data/coco under UPSNet_ROOT, and run init_coco.sh to prepare COCO dataset for UPSNet.

Training:

python upsnet/upsnet_end2end_train.py --cfg upsnet/experiments/$EXP.yaml

Test:

python upsnet/upsnet_end2end_test.py --cfg upsnet/experiments/$EXP.yaml

We provide serveral config files (16/4 GPUs for Cityscapes/COCO dataset) under upsnet/experiments folder.

Model Weights

The model weights that can reproduce numbers in our paper are available now. Please follow these steps to use them:

Run download_weights.sh to get trained model weights for Cityscapes and COCO.