-
The program got stuck just like former issues, however, I use 4 V100s, which should have enough memory. I also tried to change bs to 4 and image size to 761, it still got stuck.
-
Ubuntu 14.04.2
GPU:TITAN X;
Driver Version: 375.39
CUDA8.0;
cudnn 5.1.5
python2.7;
numpy1.8.2
mxnet 0.12.0
How to solve this problem? Thanks!
-
Thanks for the excellent work!
When wiil you release the train code of seg like sam?
-
Hi, RolandGao, nice to see a good job! I see you've done a lot of experiments on the backbone setting, but I still have some confusion after reading your published paper.
- First, You calculate th…
-
Hi, thank you for great repository !!!
When I tested pretrained model, there was error in this line.
https://github.com/sithu31296/semantic-segmentation/blob/492231c0d77088267ae6ce6b21a4107ccf8e9…
-
你好，我下载了checkpoint,用STDC1-Seg/model_maxmIOU50.pth，backbone='STDCNet813', scale=0.5进行测试，在RTX2080上运行，跑完cityscapes数据val集的500张图大概需要57s,并未达到实时啊，不知道测试时还需要设置什么参数吗？
-
Hi @jxhuang0508 @Dayan-Guan,
I tested your provided models of both deeplabv2 and FCN, and use the advent code to evaluate the three datasets, I got the same results on cityscapes, but got **largely…
-
hello could you tell the details of unzipping the file from the gui on my linux vm cause i still couldnot get the pth files by gunzip command on my linux machine (ubuntu os)
_To download the trained …
-
使用文档中的Unet分割模型转成rknn部署到瑞芯微上提示该错误：
配置文件
模型转换命令：
python paddle_infer_shape.py --model_di…
-
Is there a demo.py for sdcnet?
Where can I download pretrained sdcnet?
Thanks,