Comments (6)
Hi, that's caused by the different lengths of the data loaders of DUTS_class and COCO-SEG/COCO9213 datasets. 291 is the class number of images in the DUTS_class dataset.
So, you don't need to worry about that, the loading is on these two whole datasets.
If you set only the DUTS_class as the training set, you will see it ranges from 0/291 to 280/291.
(您表达的没问题的, 再写一遍中文就客气啦. 还有问题欢迎继续留言.)
from gconet_plus.
谢谢,我想过这个问题,不过还没来得及测试
还有个问题是我怎么训练都达不到论文中的结果,下面是我的结果
第一张图是用一张gpu训练的的,第二张图是两张卡用DataParallel的方式训练的,训练了2000个epoch,之前也试过350和500,但都差不多,比论文差,我只改了batchsize,因为2080ti显存不够,我最大只能设置6,看到论文里是26,后来用DataParallel的方式设置了12,效果也差好多
from gconet_plus.
这个你用2080Ti训, batch size只有原先的1/4还不到, performance肯定要大打折扣啊... 本来一般的deep-learning训练都可能受batch size的影响, 更加上CoSOD这个Co的部分肯定是需要更多的样本来在线挖掘共识的, 所以其实我觉得bs=6能到这个performance算是合理的水准了.
关于DataParallel的方式, 这个方式其实本来就是不能等效于扩大batchsize的, distributed的DDP会更接近等效. 但我还是推荐你用一个大点的GPU试一下, 像原文中的V100类似的.
我之前是统计过DUTS_class里每个class样本数量的, 大概bs=32能覆盖到70%的class, 设太大了也没什么意义(我试过在一个80G的A100上, 设到无限大也没什么提升), 但是你设得太小肯定是会影响训练效果的哈.
from gconet_plus.
好的,十分感谢,多卡的方式我现在用DDP的重新训练了下,之后看看结果,不过实在没有卡,只能先在目前这上面做了,再次感谢耐心回答
from gconet_plus.
没事, 或者你用loss累加多次再backward一次的方式变相增加下batch size, 这个改起来最简单, 我随便找的样例: link.
from gconet_plus.
没事, 或者你用loss累加多次再backward一次的方式变相增加下batch size, 这个改起来最简单, 我随便找的样例: link.
好的,谢谢,等这次DDP的训练完了我加上试试效果
from gconet_plus.
Related Issues (10)
- inference speed 250 fps HOT 2
- 网络权重 HOT 10
- 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
- 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.