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

[Feature] 前端实现场景分类功能 & [Style] 规范代码风格 #21

Merged
merged 5 commits into from
Sep 26, 2022
Merged

[Feature] 前端实现场景分类功能 & [Style] 规范代码风格 #21

merged 5 commits into from
Sep 26, 2022

Conversation

jscslld
Copy link
Member

@jscslld jscslld commented Sep 24, 2022 •
edited
Loading

  1. 前端实现场景分类功能。
  2. 移除不必要的前端依赖，使得可以在Node.js 16下通过CI。
  3. 统一项目名，将前端中的Hippo修改为PP-GeoView。
  4. 使用PaddleRS提供的decode_image函数进行图片读取，减少代码冗余。
  5. 修复了批量渲染函数的函数名拼写错误的问题
  6. 目标检测绘制时colormap自动生成，便于适配自定义模型

terayco and others added 4 commits September 24, 2022 15:04
@terayco
9.24更新 (#5)
73ebe70 
* 新增场景分类功能

* 1.修复绘制目标框不准确的bug
2.修复图像偏色问题
3.将目标框颜色改为更显眼的紫色

* 修改滑窗步长，加快推理速度

* 1.修改场景分类读取图像的接口，改用paddelrs中的decode_image
2.修改地物分类结果图像的颜色显示
3.去除地物分类任务中的冗余代码

* 删除地物分类中冗余代码

* 1.修改错误函数名（批量处理）
2.删除渲染函数中冗余代码
3.改用cv2统一对图像进行操作处理，去除skimage的引用
@yibaikuai
场景分类功能的前端实现
f5f2b35 
1.  前端实现场景分类功能
2.  移除不必要的依赖，使得CI可以在Node.js 16.x下通过
@jscslld
绘制图片时colormap自动生成，便于适配用户自定义模型
d1f1cbd
@jscslld
绘制图片时colormap自动生成，便于适配用户自定义模型
152cba6
Bobholamovic
Bobholamovic reviewed Sep 26, 2022
View reviewed changes
Copy link
Member

@Bobholamovic Bobholamovic left a comment

Choose a reason for hiding this comment

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

算法&后端部分基本OK。有两个想法：

  1. 滑窗尺寸和步长后续是否可以做成可调的？
  2. 滑窗推理可以使用PaddleRS原生的slider_predict()方法。
    前端部分请 @yibaikuai review~

backend/applications/image_processing/render.py Show resolved Hide resolved
backend/applications/interface/change_detection.py
@@ -41,7 +41,7 @@ def execute(model_path, data_path, out_dir, names_):
return_list=True)
# 设置滑窗大小与滑动步长
WINDOW_SIZE = 256
STRIDE = 128
STRIDE = 256
Copy link
Member

Choose a reason for hiding this comment

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

后续可以考虑把滑窗大小和步长设置为可调的，因为用户导出的模型不一定接受这个大小的输入。

backend/applications/interface/object_detection.py Outdated Show resolved Hide resolved
yibaikuai
yibaikuai approved these changes Sep 26, 2022
View reviewed changes
Copy link
Member

@yibaikuai yibaikuai left a comment

Choose a reason for hiding this comment

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

LGTM.

@Bobholamovic Bobholamovic merged commit 57f8da6 into PaddleCV-SIG:develop Sep 26, 2022
@jscslld jscslld deleted the feature/classification branch October 16, 2022 06:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Bobholamovic Bobholamovic Bobholamovic left review comments

@yibaikuai yibaikuai yibaikuai approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@jscslld @Bobholamovic @yibaikuai @terayco