mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00

unrealMJ bd29c20778

CodeCamp #150 [Feature] Add ISNet (#2400 )

## Motivation

Support ISNet.
paper link: [ISNet: Integrate Image-Level and Semantic-Level Context for
Semantic
Segmentation](https://openaccess.thecvf.com/content/ICCV2021/papers/Jin_ISNet_Integrate_Image-Level_and_Semantic-Level_Context_for_Semantic_Segmentation_ICCV_2021_paper.pdf)

## Modification

Add ISNet decoder head.
Add ISNet config.

2023-01-04 20:39:03 +08:00

2.5 KiB

Raw Blame History

ISNet

ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

Description

This is an implementation of ISNet. Official Repo

Usage

Prerequisites

Python 3.7
PyTorch 1.6 or higher
MIM v0.33 or higher
MMSegmentation v1.0.0rc2 or higher

All the commands below rely on the correct configuration of PYTHONPATH, which should point to the project's directory so that Python can locate the module files. In isnet/ root directory, run the following line to add the current directory to PYTHONPATH:

export PYTHONPATH=`pwd`:$PYTHONPATH

Training commands

mim train mmsegmentation configs/isnet_r50-d8_8xb2-160k_cityscapes-512x1024.py --work-dir work_dirs/isnet

To train on multiple GPUs, e.g. 8 GPUs, run the following command:

mim train mmsegmentation configs/isnet_r50-d8_8xb2-160k_cityscapes-512x1024.py --work-dir work_dirs/isnet --launcher pytorch --gpus 8

Testing commands

mim test mmsegmentation configs/isnet_r50-d8_8xb2-160k_cityscapes-512x1024.py --work-dir work_dirs/isnet --checkpoint ${CHECKPOINT_PATH}

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	config	download
ISNet	R-50-D8	512x1024	-	-	-	79.32	80.88	config	model

Citation

@article{Jin2021ISNetII,
  title={ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation},
  author={Zhenchao Jin and B. Liu and Qi Chu and Nenghai Yu},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021},
  pages={7169-7178}
}

2.5 KiB Raw Blame History