Comments (4)
SakuraRiven
commented on August 28, 2024
15数据集文字比较小，尺度较为固定，UNet结构dense predict比较容易。13数据集文字尺度变化比较大，不容易回归，可以尝试FPN分层预测。
loss函数可以CE+Dice一起用
生成label的时候，被切断的部分可以直接置ignore，比现在这种循环找要方便的多
from east.
ranye92
commented on August 28, 2024
15数据集文字比较小，尺度较为固定，UNet结构dense predict比较容易。13数据集文字尺度变化比较大，不容易回归，可以尝试FPN分层预测。
loss函数可以CE+Dice一起用
生成label的时候，被切断的部分可以直接置ignore，比现在这种循环找要方便的多
感谢大佬这么快就回复。我刚入门不久，具体细节还是想多问一句，烦请解惑：
第一点中FPN分层预测（我理解是提取不同尺度的feature之后，不进行concat，每个scale都输出一个预测吗？不同scale的结果该如何融合呢？）
from east.
SakuraRiven
commented on August 28, 2024
就类似于FRCNN那样，不同scale的feature map负责不同的预测，结果直接对应回原图就可以了啊。
这个只是我个人想法，当时这个repo真就写着玩的，当入门看就行，真做项目还是自己改进下
from east.
ranye92
commented on August 28, 2024
就类似于FRCNN那样，不同scale的feature map负责不同的预测，结果直接对应回原图就可以了啊。
这个只是我个人想法，当时这个repo真就写着玩的，当入门看就行，真做项目还是自己改进下
收到，感谢！
from east.
Related Issues (20)
- According to find_min_rect_angle HOT 3
- According to crop_img HOT 1
- 直接加载训练好的模型，也不能复现性能 HOT 1
- ZIP entry not valid HOT 1
- How many epochs were trained for the pretrained model?
- Question: Saving checkpoints
- what is submit.zip HOT 1
- 无法得到作者的精度 HOT 3
- ZeroDivisionError: float division by zero
- 请帮忙看看，测试不了是什么情况 HOT 2
- 执行python train.py 遇到以下问题。望回复 HOT 1
- The sample not present in GT
- add languages
- RGBA support with png images
- Error loading the ZIP archive HOT 1
- Windows运行EAST
- CUDA out of memory on eval.py
- In dataset.py crop_img function sometimes returning negative vertices
- 有没有中文权重文件
- AP
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from east.