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.

Sign up for GitHub

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

Jump to bottom

[Tutorials-4] —3D image classification from CT scans.ipynb #5384

Merged
merged 16 commits into from
Feb 6, 2023
Merged

[Tutorials-4] —3D image classification from CT scans.ipynb #5384

merged 16 commits into from
Feb 6, 2023

Conversation

WangXi2016
Copy link
Contributor

@WangXi2016 WangXi2016 commented Oct 28, 2022 •
edited

test=document_fix

@paddle-bot
Copy link

paddle-bot bot commented Oct 28, 2022

感谢你贡献飞桨文档，文档预览构建中，Docs-New 跑完后即可预览，预览链接：http://preview-pr-5384.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html
预览工具的更多说明，请参考：[Beta]飞桨文档预览工具

@CLAassistant
Copy link

CLAassistant commented Oct 28, 2022 •
edited

CLA assistant check
All committers have signed the CLA.

@paddle-bot
Copy link

paddle-bot bot commented Oct 28, 2022 •
edited

✅ This PR's description meets the template requirements!
Please wait for other CI results.

@WangXi2016 WangXi2016 changed the title Create [Tutorials-4] —3D image classification from CT scans.ipynb [Tutorials-4] —3D image classification from CT scans.ipynb Oct 28, 2022
@momozi1996 momozi1996 mentioned this pull request Nov 4, 2022
Closed
@WangXi2016
Create [Tutorials-2] —Crowd Instance-level Human Parsing Dataset 数据集上…
5e1965b 
…使用DeepLabV3+实现多分类语义分割.ipynb
@WangXi2016
[Tutorials_2]__Crowd_Instance_level_Human_Parsing_Dataset_数据集上使用DeepL…
7e8c502 
…abV3+实现多分类语义分割.ipynb
@WangXi2016
Merge branch 'new_branch' of https://github.com/WangXi2016/docs into …
309479c 
…new_branch
@WangXi2016
Revert "Create [Tutorials-4] —3D image classification from CT scans.i…
33c07d5 
…pynb"

This reverts commit 0152fd2.
@WangXi2016
Revert "Create [Tutorials-2] —Crowd Instance-level Human Parsing Data…
746f982 
…set 数据集上使用DeepLabV3+实现多分类语义分割.ipynb"

This reverts commit 5e1965b.
@WangXi2016
Create [Tutorials-4] —3D image classification from CT scans.ipynb
3adc3b8
@WangXi2016
Delete [Tutorials_2]__Crowd_Instance_level_Human_Parsing_Dataset_数据集上…
86a31a7 
…使用DeepLabV3+实现多分类语义分割.ipynb
@WangXi2016
Update [Tutorials-4] —3D image classification from CT scans.ipynb
81bd9a4
shiyutang
shiyutang suggested changes Nov 22, 2022
View reviewed changes
Copy link
Contributor

@shiyutang shiyutang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  1. 存在重复import的random、os、zipfle等，最好import的内容都在一个block中实现，其他位置不出现。
  2. 完整数据集链接实际是论文链接，不是数据集链接，需修改。
  3. 第四部分下的block L37-L42 存在代码冗余，建议全部去除，直接当成参数传入。
  4. dataset类的空格太多，建议报错方法间一行代码。其他部分的空格也需要注意删减。
  5. 存在由于使用面向过程思想，代致的代码逻辑结构不明晰，建议训练和predict部分均修改为trainer 和 predictor，使用面向对象的编程方式优化代码。
  6. 代码运行完成，无报错，能得到预期效果。

@momozi1996
Copy link
Collaborator

@WangXi2016 hello~~ ~请按照RD的意见好好修改哈～～

@WangXi2016
Copy link
Contributor Author

@shiyutang 已经按照要求修改，第二条的完整数据集链接，参考的原文档就是的这个链接。

@shiyutang
Copy link
Contributor

建议二维CNN | Conv2D的图片可以适当缩小；三维CNN | Conv3D的图片可以适当缩小。其他无明显问题。

@WangXi2016
Copy link
Contributor Author

已缩小图片 @shiyutang

shiyutang
shiyutang approved these changes Jan 17, 2023
View reviewed changes
Copy link
Contributor

@shiyutang shiyutang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@sunzhongkai588
Copy link
Collaborator

sunzhongkai588 commented Jan 31, 2023 •
edited

不是特别熟悉3D方面的数据，有些问题可能是我理解有问题，辛苦简短回答一下～

  1. “3D深度” 是什么意思？
    image

  2. “体积“可以旋转嘛？用词是否准确
    image

  3. BCEloss可以加一个相关api文档的链接
    image

  4. “变异性”是？如果是专有名词，可以在后面加括号和英文
    image

@WangXi2016
Copy link
Contributor Author

WangXi2016 commented Feb 2, 2023 •
edited

我修改了一下，看看会不会更好理解一些 @sunzhongkai588

sunzhongkai588
sunzhongkai588 approved these changes Feb 2, 2023
View reviewed changes
Copy link
Collaborator

@sunzhongkai588 sunzhongkai588 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

jzhang533
jzhang533 reviewed Feb 3, 2023
View reviewed changes
Copy link
Collaborator

@jzhang533 jzhang533 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

2、导入相关库

这个小节里的代码实现里，假定了用户要在AIStudio上运行这个教程。实际上，不应该有这样的假定。

当我们说卷积神经网络（CNN）时，通常是指用于图像分类的二维CNN。但是，现实世界中还使用了其他两种类型的卷积神经网络，即1维CNN和3维CNN。在本指南中，我们将介绍1D和3D CNN及其在现实世界中的应用。我假设您已经大体上熟悉卷积网络的概念。 初学者可能会理解为1维CNN处理一维的数据，2维CNN处理二维的数据，这是错误的！！！

在卷积神经网络（CNN）中，一维和二维滤波器并不是真正的一维和二维。这是只是描述的惯例。
  • 这个段落，没有讲清楚1D、2D、3D卷积的含义。虽然加感叹号说那么理解不对，但也没说正确的理解是什么。建议进一步查阅资料，重新组织这个段落的语言。
  • 出现了两种术语：1维CNN 和 1D CNN，建议统一。

@WangXi2016
Copy link
Contributor Author

@jzhang533 貌似不大好描述我直接删掉了，该段落下面就是各种维度的卷积的描述，名词已经统一

jzhang533
jzhang533 approved these changes Feb 6, 2023
View reviewed changes
Copy link
Collaborator

@jzhang533 jzhang533 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jzhang533 jzhang533 merged commit fb7f68e into PaddlePaddle:develop Feb 6, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jzhang533 jzhang533 jzhang533 approved these changes

@shiyutang shiyutang shiyutang approved these changes

@sunzhongkai588 sunzhongkai588 sunzhongkai588 approved these changes

Assignees

@sunzhongkai588 sunzhongkai588

Labels
contributor status: proposed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
6 participants
@WangXi2016 @CLAassistant @momozi1996 @shiyutang @sunzhongkai588 @jzhang533