Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CodeCamp #150 [Feature] Add ISNet #2400

Merged
merged 48 commits into from
Jan 4, 2023
Merged
Changes from 1 commit
Commits
Show all changes
48 commits
Select commit Hold shift + click to select a range
f2b8d2f
doc
BLUE-coconut Nov 30, 2022
67b51b7
[Doc]Translate the 1_config.md and modify a wrong statement in 1_conf…
pofengdenihong Dec 2, 2022
4287fd2
Translate the 1_config.md and modify a wrong statement in 1_config.md
pofengdenihong Dec 2, 2022
5668182
modify part of content
BLUE-coconut Dec 3, 2022
ad470a3
Modify some expressions
pofengdenihong Dec 5, 2022
104a24d
changed parts of content
BLUE-coconut Dec 5, 2022
b0e57c6
Apply suggestions from code review
MeowZheng Dec 6, 2022
9750c97
Merge pull request #2371 from pofengdenihong/dev-1.x
MeowZheng Dec 6, 2022
8a3d6cd
[Doc] Add ZN datasets.md in dev-1.x
MengzhangLI Dec 6, 2022
3d1f8b7
modified
BLUE-coconut Dec 7, 2022
addd38d
fix typo
MengzhangLI Dec 7, 2022
372a6ce
Update docs/zh_cn/user_guides/4_train_test.md
BLUE-coconut Dec 7, 2022
dc8aa35
CodeCamp #1562 [Doc] update `overview.md`
tianleiSHI Dec 10, 2022
dddf093
Update overview.md
tianleiSHI Dec 10, 2022
e9cdd75
support isnet(ICCV 2021)
unrealMJ Dec 11, 2022
7edb141
Merge pull request #2355 from BLUE-coconut/master
MeowZheng Dec 12, 2022
b770884
Add torch1.13 in CI
xiexinch Dec 12, 2022
02030b1
use mim install mm packages
xiexinch Dec 12, 2022
d755707
Update docs/zh_cn/overview.md
tianleiSHI Dec 12, 2022
c2042f3
Update docs/zh_cn/overview.md
tianleiSHI Dec 12, 2022
fdd1b95
install all requirements
xiexinch Dec 12, 2022
7537987
Merge pull request #2397 from tianleiSHI/dev-1.x
MeowZheng Dec 12, 2022
492313b
install wheel
xiexinch Dec 13, 2022
815b24e
add ref
xiexinch Dec 13, 2022
d7b85aa
Merge pull request #2402 from xiexinch/add-torch1.13-in-ci-1.x
MeowZheng Dec 13, 2022
164fd3f
fix
MengzhangLI Dec 13, 2022
e88489e
fix
MengzhangLI Dec 13, 2022
eeee12e
Merge pull request #2387 from MengzhangLI/zn_datasets_1.x
MeowZheng Dec 13, 2022
f5b4c12
add example project
xiexinch Dec 15, 2022
81da7aa
add ci ignore
xiexinch Dec 15, 2022
532ff5b
DOC
tianleiSHI Dec 17, 2022
55abb68
Add docstring, update isnet code.
unrealMJ Dec 18, 2022
f7f5b7a
Update code style.
unrealMJ Dec 18, 2022
ab690bd
Update docs/zh_cn/get_started.md
tianleiSHI Dec 20, 2022
ca68b00
Merge pull request #2417 from tianleiSHI/get_started_doc
MeowZheng Dec 20, 2022
534b27b
add version limits
xiexinch Dec 20, 2022
8539e22
Merge pull request #2412 from xiexinch/mmseg_projects
MeowZheng Dec 20, 2022
816c2e0
Merge branch 'dev-1.x' into majie/isnet
unrealMJ Dec 21, 2022
88830fa
move isnet code to /projects
unrealMJ Dec 21, 2022
f359ea8
update README and config
unrealMJ Dec 21, 2022
e0a37ff
Update README.
unrealMJ Dec 21, 2022
b5109cd
fix lint error
unrealMJ Dec 22, 2022
bb6fea8
Merge remote-tracking branch 'upstream/dev-1.x' into majie-isnet
xiexinch Jan 3, 2023
c2123dc
update ckpt link
xiexinch Jan 3, 2023
af0985a
rename config
xiexinch Jan 3, 2023
2deee33
update readme table
xiexinch Jan 4, 2023
b852ab1
update link
xiexinch Jan 4, 2023
71a6331
Update projects/isnet/README.md
MeowZheng Jan 4, 2023
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
CodeCamp #1562 [Doc] update overview.md
  • Loading branch information
tianleiSHI committed Dec 10, 2022
commit dc8aa351d9e1275d8c13356e8dd2075053913c22
74 changes: 74 additions & 0 deletions docs/zh_cn/overview.md
Original file line number Diff line number Diff line change
@@ -1 +1,75 @@
# 概述

本章节向您介绍 MMSegmentation 框架以及语义分割相关的基本概念。我们还提供了关于 MMSegmentation 的详细教程链接。

## 什么是语义分割?

语义分割是将图像中属于同一目标类别的部分聚类在一起的任务。它也是一种像素级预测任务,因为图像中的每一个像素都将给根据类别进行分类。该任务的一些示例基准有 [Cityscapes](https://www.cityscapes-dataset.com/benchmarks/), [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/) 和 [ADE20K](https://groups.csail.mit.edu/vision/datasets/ADE20K/) 。通常用平均交并比 (Mean IoU) 和像素准确率 (Pixel Accuracy) 这两个指标来评估模型。

## 什么是 MMSegmentation?

MMSegmentation 是一个工具箱,它为语义分割任务的统一实现和模型评估提供了一个框架,并且高质量实现了常用的语义分割方法和数据集。

MMSeg 主要包含了 apis, structures, datasets, models, engine, evaluation and visualization 这七个主要部分。

- **apis** 提供了模型推理的高级api

- **structures** 提供了分割任务的数据结构 `SegDataSample`

- **datasets** 支持用于语义分割的多种数据集

- **transforms** 包含多种数据增强变换

- **models** 是分割器最重要的部分,包含了分割器的不同组件

- **segmentors** 定义了所有分割模型类
- **data_preprocessors** 用于预处理模型的输入数据
- **backbones** 包含各种骨干网络,可将图像映射为特征图
- **necks** 包含各种模型颈部组件,用于连接分割头和骨干网络
- **decode_heads** 包含各种分割头,将特征图作为输入,并预测分割结果
- **losses** 包含各种损失函数

- **engine** 是运行时组件的一部分,扩展了 [MMEngine](https://github.com/open-mmlab/mmengine) 的功能

- **optimizers** 提供了优化器和优化器封装
- **hooks** 提供了 runner 的各种钩子

- **evaluation** 提供了评估模型性能的不同指标

- **visualization** 分割结果的可视化工具

## 如何使用本指南?

以下是详细步骤,将带您一步步学习如何使用 MMSegmentation :

1. 有关安装说明,请参阅 [开始你的第一步](getting_started.md)。

2. 对于初学者来说,MMSegmentation 是开始语义分割之旅的最好选择,因为这里实现了许多 SOTA 模型以及经典的模型 [model](model_zoo.md) 。另外将 building 块和一些高级 apis 连接在一起,可以更便捷的执行分割任务。关于 MMSegmentation 的基本用法,请参考下面的教程:

- [配置](user_guides/1_config.md)
- [数据预处理](user_guides/2_dataset_prepare.md)
- [推理](user_guides/3_inference.md)
- [训练和测试](user_guides/4_train_test.md)

3. 如果你想了解 MMSegmentation 工作的基本类和功能,请参考下面的教程来深入研究:

- [数据流](advanced_guides/data_flow.md)
- [结构](advanced_guides/structures.md)
- [模型](advanced_guides/models.md)
- [数据集](advanced_guides/datasets.md)
- [评估](advanced_guides/evaluation.md)

4. MMSegmentation 也为用户自定义和一些前沿的研究提供了教程,请参考下面的教程来建立你自己的分割项目:

- [添加新的模型](advanced_guides/add_models.md)
- [添加新的数据集](advanced_guides/add_dataset.md)
- [添加新的 transform](advanced_guides/add_transform.md)
- [自定义 runtime](advanced_guides/customize_runtime.md)

5. 如果您更熟悉 MMSegmentation v0.x , 以下是 MMSegmentation v0.x 迁移到 v1.x 的文档

- [迁移](migration/index.rst)

## 参考来源

- https://paperswithcode.com/task/semantic-segmentation/codeless#task-home