Comments (10)
嗨, 那您的performance是多少呢?
我记得应该就是这个权重文件, 他俩确实就是同一个, 只是标注明显一点而已.
那您有没有用过比如ultimate_duts.pth
测一下看看和文中一不一致呢? 如果DUTS训的权重也和论文里的不一致, 那应该不是我传错了, 而是其他问题比如环境配置不一致导致结果不同.
from gconet_plus.
第一个为best,第二个为duts跑出的结果,都与论文中不同。我再尝试一下您的环境配置,感谢回复~
from gconet_plus.
没事, 不用客气.
我README里面有提供colab一整套直接一键run的test+evaluation的, 你可以试一下.
我刚刚也用它跑了下ultimate_duts_cocoseg (The best one).pth on CoCA
的结果, 略有极小出入(Emax还比论文里的高了不到0.001)但是基本一致:
torch==1.13.1:
torch==2.0.0:
所以应该是你那里有一点小问题.
from gconet_plus.
感谢您,我也尝试了。
我还有另外的问题,我想在推理阶段生成DUTS和COCO-seg的预测图,中途显存为什么会爆掉呢?
from gconet_plus.
这个我不清楚啊, 毕竟colab上16G的T4也能跑.
from gconet_plus.
您好,我又在colab上尝试了几次,推理时生成coco-seg的预测图还是会出现out of memory,应该也不是梯度未清零的原因吧
from gconet_plus.
您好,我已经解决了,原因是推理时数据加载方式和训练时不同
from gconet_plus.
您好,我又在colab上尝试了几次,推理时生成coco-seg的预测图还是会出现out of memory,应该也不是梯度未清零的原因吧
哦对, 我想起来了... 因为inference时是默认加载整个group的. 而coco-seg的不同组的图像数量分布夸张得不均匀, 比如person这一group, 直接就几个G, 那你全读入去处理, 显存肯定是放不下的. 你换成正常的测试集就肯定没问题的.
from gconet_plus.
您好,我已经解决了,原因是推理时数据加载方式和训练时不同
哈哈, 好吧, 弄明白就好. 有问题欢迎继续留issue.
from gconet_plus.
是的,感谢您的及时回复,非常感谢~
from gconet_plus.
Related Issues (10)
- inference speed 250 fps HOT 2
- 与select_results.py相关的问题
- 一些与sort_results.py和select_resulets.py相关的问题 HOT 6
- 所提供的代码和训练命令训练时是默认使用了DUTS class和COCO-SEG吗 HOT 12
- Why does an epoch stop early and go straight to the next epoch? HOT 6
- simple inference ? HOT 8
- 关于RefUnet(nn.Module)模块的问题 HOT 5
- Class_Activation_Mapping HOT 4
- cocoseg数据集问题 HOT 5
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 gconet_plus.