Lei

Hi. I have uploaded the lists of training and validation images in the > /datasets directory, please check. However, I have not run the experiments for quite some time and...

> 按照您的代码里的内容，数据集应该有三部分，应该还有测试集，不知道您的测试集是哪些图像呢 During the contest, there was a testing set that can be evaluated on the test server. However, the released SECOND dataset does not provide labels for the testing...

> Please check the detailed split of train/test sets in the '/datasets' folder

Yes, I have run experiments on this dataset. Please refer to the paper in this [repository](https://github.com/ggsDing/SCanNet)

In the published paper the highest mIoU is 73.41. Did you do experiments with your own settings?

> > > In the published paper the highest mIoU is 73.41. Did you do experiments with your own settings? > > > > > > Maybe I didn't make...

You can just run SSCD-l as the baseline. Also you are welcome to check my new paper in this repository: [link](https://github.com/ggsDing/SCanNet)

Hi, What's the model you used and what's the accuracy? It is hard to assess your result based on the prediction maps of a single area. Some images are just...

> That's strange. I'll run the released codes and see what's wrong

> And by the way, since the original SECOND dataset only has RGB labels and I want to use class-indexed labels just the same as your scripts default choice, I...