Comments (8)
tan90du-sx
commented on July 30, 2024
盼回复
from ieee_tip_uiu-net.
BLUE-coconut
commented on July 30, 2024
我之前一开始碰到这个问题，后来发现是直接用作者的dataloader可能image和label没有对齐，我改了loader的方法就解决了，和原论文对的上的。你可以看看是不是这个问题。
from ieee_tip_uiu-net.
Li-Haoqing
commented on July 30, 2024
麻烦您能具体的说一下吗？谢谢！
@BLUE-coconut
from ieee_tip_uiu-net.
BLUE-coconut
commented on July 30, 2024
就是它SalObjDataset构造数据集时是根据传入的img_name_list和lbl_name_list 的顺序来构造的，而它test.py中img_name_list = glob.glob(image_dir + os.sep + '')和label_name_list = glob.glob(label_dir + os.sep + '')不能保证img_name_list[i]和label_name_list [i]是同一张图像的原图和mask，导致你实际上SalObjDataset中的‘image’和‘label’也是不对应的，所以计算出来的实验指标有问题。
from ieee_tip_uiu-net.
Li-Haoqing
commented on July 30, 2024
from ieee_tip_uiu-net.
Joazs
commented on July 30, 2024
您好，请问为什么在测试中要经过一个normPRED？网络中不是已经经过了Sigmoid了吗？
from ieee_tip_uiu-net.
Web-AK
commented on July 30, 2024
谢谢
from ieee_tip_uiu-net.
BLUE-coconut
commented on July 30, 2024
hello，不好意思最近有点忙，才看到。一个比较简单粗暴的方式就是，先读取train image的图片名，例如：Misc_1.png，你用split函数提取出“Misc_1”，然后，test image图片名就是“Misc_1”+“_pixels0.png”
1367012021
***@***.***
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2023年11月3日(星期五) 下午4:54
收件人: ***@***.***>;
抄送: "HaoLan ***@***.***>; ***@***.***>;
主题: Re: [danfenghong/IEEE_TIP_UIU-Net] #测试Quantification_Results和Verification_data数据结果均接近于0？？ (Issue #4)
@BLUE-coconut 大佬，您好！
想问一下loader的方法具体需要怎么修改才能跟原论文对的上。我发现了这个问题，但我这个小白，不知道如何去修改？
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
from ieee_tip_uiu-net.
Related Issues (19)
- forget to upload model
- 关于传统算法指标计算问题
- requirements and IoU values HOT 3
- 为什么我测试出来iou比niou还小
- Modify input shape
- RuntimeError: torch.cat(): input types can't be cast to the desired output type Byte HOT 5
- 建议requirements中依赖包的版本指明
- train_data问题
- test.py代码的问题
- 不能生成预测的图片吗？
- How to train a custom dataset and visualize test results?
- 你好，请问什么时候开源全部代码？ HOT 8
- 在test.py中IoU=total_IoU/20为什么除以20？ HOT 1
- What is the difference between your work and the U^2 net? HOT 2
- YOLOv7添加该网络 HOT 1
- the model is available just for chinese HOT 1
- 请问论文中所述Synthetic dataset 选取6200张图像，具体是怎么实现的？
- Provide tutorial
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 ieee_tip_uiu-net.