sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

Last update: Jan 02, 2023

Overview

Introduction

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

Documents

In English

https://sssegmentation.readthedocs.io/en/latest/

Supported

Supported Backbones

Supported Models

Supported Datasets

Citation

If you use this framework in your research, please cite this project.

@misc{ssseg2020,
    author = {Zhenchao Jin},
    title = {SSSegmentation: A general framework for strongly supervised semantic segmentation},
    year = {2020},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\url{https://github.com/SegmentationBLWX/sssegmentation}},
}

References

[1]. https://github.com/open-mmlab/mmcv
[2]. https://github.com/open-mmlab/mmsegmentation

Comments

Training on custom dataset with 4 channels

Hi, I want to train my own dataset which has images in 4 channels - RGB images and IR(infrared) images. Could you help me out with that? How can i modify the codes of this repo to accommodate that extra channel?

opened by cspearl 4
how to train with multi-gpu in one machine

hi，i wanna train the model with 4 gpus in one machine however, your code 'distrain.sh' and 'train.py' can only train with distributed mode in multi-machine how can i modify the code ?

opened by Kenneth-X 3
isnet:imagelevel.py

imagelevel.py : 47: feats_il = self.correlate_net(x, torch.cat([x_global, x], dim=1))

isanet.py： 47：context = super(SelfAttentionBlock, self).forward(x, x)

is there any problem？ bug？

opened by shujunyy123 3
How to modify parameters to use single card training?

How to modify parameters to use single card training?

In addition to modifying the following in config:

SEGMENTOR_CFG.update(distributed{'is_on':False})

opened by kakamie 1
SWIN-B with DeepLabv3+ training on custom dataset

Hi, I am learning about Segmentation and want to try out the segmentation my custom data set. Could you please provide steps on how to use supported backbones with some particular architectures?

If I want to use SWIN-B as my backbone on DeepLabV3+ using a custom dataset, what should be the commands and all. I could not find anything on the docs and on the github page. Could you please help.

opened by deshwalmahesh 1
Is there should be 'continue'?

https://github.com/SegmentationBLWX/sssegmentation/blob/7a405b1a4949606deae067223ebd68cceec6b225/ssseg/modules/models/memorynet/memory.py#L176

If there are more than one 'num_feats_per_cls' in the furture, 'break' will make this for loop only update the first memory_feature?

opened by EricKani 1
医学图像分割也很有意义，我想给你一些公开的医学图像数据集。哈哈哈哈
Hi @CharlesPikachu ！UNet 也是大名鼎鼎的分割模型啊，它在医学图像分割领域是 SOTA，个人认为 Supported Models 列表里应该有名字，而且应该在 FCN 之后。哈哈哈 🥇

虽然 PyTorch Hub 已经有预训练的 UNet 了，但我想要皮卡丘也有！ 🛩️

这里提供一些医学数据集给你参考：

PyTorch Hub 里预训练 UNet 的数据集：LGG Segmentation Dataset

DDTI，已经按照下一个数据集的格式预处理过，百度网盘提取码：qxds

tn-scui2020，来自比赛 tn-scui2020

百度 AI Studio 医学影像数据集集锦

List of Medical Datasets，来自 GitHub
opened by S-HuaBomb 1

Releases(v1.0.0)

Owner

GitHub Repository

tensorflow code for inverse face rendering

InverseFaceRender This is tensorflow code for our project: Learning Inverse Rendering of Faces from Real-world Videos. (https://arxiv.org/abs/2003.120

18 Nov 16, 2022

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

CO-PILOT CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum, NeurIPS 2021, Shuang Ao, Tianyi Zhou, Guodong Long, Qingh

1 Feb 18, 2022

Unofficial implementation of MUSIQ (Multi-Scale Image Quality Transformer)

MUSIQ: Multi-Scale Image Quality Transformer Unofficial pytorch implementation of the paper "MUSIQ: Multi-Scale Image Quality Transformer" (paper link

41 Jan 02, 2023

MlTr: Multi-label Classification with Transformer

MlTr: Multi-label Classification with Transformer This is official implement of "MlTr: Multi-label Classification with Transformer". Abstract The task

38 Nov 08, 2022

PyTorch Implementation for Fracture Detection in Wrist Bone X-ray Images

wrist-d PyTorch Implementation for Fracture Detection in Wrist Bone X-ray Images note: Paper: Under Review at MPDI Diagnostics Submission Date: Novemb

5 Oct 12, 2022

A self-supervised 3D representation learning framework named viewpoint bottleneck.

Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck Paper Created by Liyi Luo, Beiwen Tian, Hao Zhao and Guyue Zhou from Institute for AI In

63 Aug 11, 2022

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Autoregressive Image Generation using Residual Quantization (CVPR 2022) The official implementation of "Autoregressive Image Generation using Residual

529 Dec 30, 2022

OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

OrienMask This repository implements the framework OrienMask for real-time instance segmentation. It achieves 34.8 mask AP on COCO test-dev at the spe

45 Dec 13, 2022

[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search paper | website One Proxy Device Is Enough for Hardware-Aware Neural Architec

10 Dec 16, 2022

TCube generates rich and fluent narratives that describes the characteristics, trends, and anomalies of any time-series data (domain-agnostic) using the transfer learning capabilities of PLMs.

TCube: Domain-Agnostic Neural Time series Narration This repository contains the code for the paper: "TCube: Domain-Agnostic Neural Time series Narrat

7 Oct 31, 2021

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

Related tags

Overview

Introduction

Documents

In English

Supported

Supported Backbones

Supported Models

Supported Datasets

Citation

References

Comments

Training on custom dataset with 4 channels

how to train with multi-gpu in one machine

isnet:imagelevel.py

How to modify parameters to use single card training?

SWIN-B with DeepLabv3+ training on custom dataset

Is there should be 'continue'?

医学图像分割也很有意义，我想给你一些公开的医学图像数据集。哈哈哈哈

Releases(v1.0.0)

Owner

tensorflow code for inverse face rendering

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

Unofficial implementation of MUSIQ (Multi-Scale Image Quality Transformer)

MlTr: Multi-label Classification with Transformer

PyTorch Implementation for Fracture Detection in Wrist Bone X-ray Images

A self-supervised 3D representation learning framework named viewpoint bottleneck.

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

TCube generates rich and fluent narratives that describes the characteristics, trends, and anomalies of any time-series data (domain-agnostic) using the transfer learning capabilities of PLMs.

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Code in both PyTorch and TensorFlow

Set of models for classifcation of 3D volumes

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

Qt-GUI implementation of the YOLOv5 algorithm (ver.6 and ver.5)

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Neural Scene Flow Prior (NeurIPS 2021 spotlight)

PyAF is an Open Source Python library for Automatic Time Series Forecasting built on top of popular pydata modules.

这是一个利用facenet和retinaface实现人脸识别的库，可以进行在线的人脸识别。

Code for WSDM 2022 paper, Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation.

Python implementation of Wu et al (2018)'s registration fusion