Comments (8)
Joazs
commented on June 28, 2024
蹲个楼，方便找。
from ieee_tip_uiu-net.
danfenghong
commented on June 28, 2024
已经开源，感谢对我们工作的关注。
速冻鱼蛋 ***@***.***> 于2022年12月20日周二 10:14写道：
… 蹲个楼，方便找。
—
Reply to this email directly, view it on GitHub
<#2 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZXKXQZYP7YW4EDW533WOEI7ZANCNFSM6AAAAAASUIGW74>
.
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
from ieee_tip_uiu-net.
Joazs
commented on June 28, 2024
您好。我在阅读您的代码遇到一个我不懂的问题。
我在看utils.py下的save_Pred_GT方法时，看到predsss=np.array((pred>0).cpu()).astype('int64')*255。
输出的预测维度是[B,1,256,256]，我想知道为什么将像素预测值>0的视为目标像素？输出预测的通道数=1的物理意义是什么？
因为我之前一直都是将分割视为2类(目标，背景)。
from ieee_tip_uiu-net.
danfenghong
commented on June 28, 2024
你好，感谢对我们工作的关注。
在我们的工作中，我们使用的Sigmoid只对一个类别建模
(通常就是正确的那个类别)，跟softmax最后激活的做法有明显差别，Softmax是对两个类别 (正反两类，通常定义为0/1的label) 建模。
希望对你的工作有帮助。
祝好！
速冻鱼蛋 ***@***.***> 于2022年12月29日周四 16:00写道：
… 您好。我在阅读您的代码遇到一个我不懂的问题。
我在看utils.py下的save_Pred_GT方法时，看到predsss=np.array((pred>0).cpu()).astype('int64')*255。
输出的预测维度是[B,1,256,256]，我想知道为什么将像素预测值>0的视为目标像素？输出预测的通道数=1的物理意义是什么？
因为我之前一直都是将分割视为2类(目标，背景)。
—
Reply to this email directly, view it on GitHub
<#2 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZVGLM35ZXQVAZZDUBTWPVAJXANCNFSM6AAAAAASUIGW74>
.
You are receiving this because you commented.Message ID:
***@***.***>
from ieee_tip_uiu-net.
Joazs
commented on June 28, 2024
您好，您的论文写的是将图像调整成320320大小进行训练和推理。而当我自己去训练时按您的设置RescaleT(320),RandomCrop(288)发现图像是288288大小的.而我设置RescaleT(320),RandomCrop(320)时候却报错：ValueError: low >= high。请问按您的代码，如何将图像调整成320*320大小？
from ieee_tip_uiu-net.
danfenghong
commented on June 28, 2024
本来就是RescaleT（320）后再RandomCrop（288），内尺寸就是288
速冻鱼蛋 ***@***.***> 于2023年2月24日周五 14:57写道：
… 您好，您的论文写的是将图像调整成320
*320大小进行训练和推理。而当我自己去训练时按您的设置RescaleT(320),RandomCrop(288)发现图像是288*288大小的.而我设置RescaleT(320),RandomCrop(320)时候却报错：ValueError:
low >= high。请问按您的代码，如何将图像调整成320*320大小？
—
Reply to this email directly, view it on GitHub
<#2 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZUKYSEBCHWKKZ3WOPDWZBLWPANCNFSM6AAAAAASUIGW74>
.
You are receiving this because you commented.Message ID:
***@***.***>
from ieee_tip_uiu-net.
Joazs
commented on June 28, 2024
你好，请问论文的录用过程是怎么样的？什么时候投稿、返修、录用？TIP好中吗？
from ieee_tip_uiu-net.
danfenghong
commented on June 28, 2024
关于TIP相关论文录用过程网上有很多信息可供参考。我们单方面没法给出一个比较具有参考价值的建议。谢谢关注。
速冻鱼蛋 ***@***.***> 于2023年9月12日周二 11:01写道：
… 你好，请问论文的录用过程是怎么样的？什么时候投稿、返修、录用？TIP好中吗？
—
Reply to this email directly, view it on GitHub
<#2 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFL2GZQF3QP2ZQDY2ZNTJ63XZ7F67ANCNFSM6AAAAAASUIGW74>
.
You are receiving this because you commented.Message ID:
***@***.***>
from ieee_tip_uiu-net.
Related Issues (18)
- forget to upload model
- 在test.py中IoU=total_IoU/20为什么除以20？ HOT 1
- #测试Quantification_Results和Verification_data数据结果均接近于0？？ HOT 8
- 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
- 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？
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.