代码小白
代码小白
Hello！This is a good job. I think that the new metrics (mCSD and mOCD) you designed is meaningful. But it seems that these new metrics are not included in the...
In paper, you use two dataset, cityscapes and helen face. however, in your code, there are not the define about helen dataset.
The pre-training model of the published coco data set is not problematic, and the test results are poor. 
Can you share your pre-training model
在运行download_pretrained_mask2image_city.sh文件时，显示latest_net_G.pt共享文件或文件夹已被移除，能否补发一份