Comments (4)
你好,
- 我们的模型是在验证集上测试的;如果需要在测试集上测的话,需要把预测结果提交到Pascal VOC的online server才能获得指标结果
- 在1/4等半监督设定下,我们的unlabeled data都是来自于trainset(剩下的3/4的图像),而没有用到任何的validation set的图像
from st-plusplus.
很感谢您的回复,
1.我注意到模型默认代码的输出结果是在验证集上测试的,不改动代码的情况下是1/8的设定下,但是我尝试自写代码去提交到Pascal VOC的server上过去几天了仍然没有反应,始终显示评估中,因此怀疑可能是自己生成的格式内容等有问题,因此希望开放下生成测试数据的代码;还是说服务器在2012挑战赛后已经停了,只需在验证集上测试即可?
2.对于这个问题我的疑问是我注意到Pascal VOC2012数据集的语义分割有标注数据train为1464,val为1449,累计2913,但是文中提到1/4规模的有标注数据用了2645张监督数据图片,是这里我的理解哪里有问题吗?譬如1/4实际上是带上了无标签数据的1/4?亦或是我注意到有人使用了benchmark_LELEASE数据集作为额外的train数据集,是两个数据集合起来1/4这样?
十分感谢您的耐心回复,给您带来的不便深感抱歉
from st-plusplus.
- 一般来说直接在验证集上测试即可,大家现在基本都是report这上面的结果,online server可能是已经关闭了,不过即使没关闭也有次数限制,没有办法短时间内提交很多setting下的结果去测试
- 这里用了1/4的图像但是有2,645张是因为,我们整体有10,582张训练图像,这其中包括1,464张Pascal VOC原始的训练图像,以及其余的经过SBD数据集扩充的训练图像,可以参考我们实验章节的第一段,具体的数据我们也提供在了这个repo的README里
from st-plusplus.
好的,十分感谢,我的疑问都没问题了,谢谢哥
from st-plusplus.
Related Issues (20)
- Supervised training HOT 4
- pseudo- labels生成之后,更新labelled data的问题 HOT 2
- Why "Re-initialize S" in Algorithm2? HOT 2
- 作者你好,我想问一下unlable.txt的文件怎么来的。unlable的标签不应该是没有的吗? HOT 4
- Experiments Question HOT 1
- 有关于灰度图像 HOT 1
- torch.version? HOT 1
- Using the best model to do pseudo labeling HOT 2
- 最终的IOU HOT 3
- How to deal with the descending in retraining with all data in mode of ST++? HOT 4
- 监督训练过程 HOT 3
- 训练过程中的报错 HOT 1
- 数据集的文件放置 HOT 2
- @yyamx 你好,你使用的是Pasca VOC数据集吗?
- 测试验证集
- RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM HOT 1
- 关于 checkpoints 程式码和论文的叙述,似乎不同
- How to test our own custom data set? HOT 3
- 预训练模型选择
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 st-plusplus.