shifangtian
shifangtian
> what is your gcc and cuda version? my gcc may be the owned version of anaconda I have no cuda,whether there must be cuda?
> @sainatarajan for compiling pytorch, CUDA is a must. May be you are getting the error because of that. Try ´nvcc --version´ in your terminal now I have already a...
> what is your gcc and cuda version? my cuda version is 9.0
I was giving an error when I am doing python setup.py build develop .error: command 'D:\\deeplearning\\anaconda\\Library\\mingw-w64\\bin\\gcc.exe' failed with exit status 1
> Can you provide more information? you solved it? no,it still exists.my cuda is 9.0 ,gpu:gtx1660,dataset:cityscapes,batchsize:2
> 嗨，您的GPU内存有多大？ > 另外，输入'img'和'mask'，您可以在PIL库中使用resize方法。 > 这两个句子添加到哪一行？ Did you solve this problem? I got the same problem
Thank you very much for your reply. Did you use Resnet50 to train from scratch instead of using the original pre-training checkpoint? So how do I modify the code if...
It ’s a pity that my GPU memory is only 11g ------------------ 原始邮件 ------------------ 发件人: "yuki-0321"
cuda9.0 cudnn7.0 pytorch-gpu1.1.0 ------------------ 原始邮件 ------------------ 发件人: "Towaki"
> Thanks for sharing. > I just trained the model with default parameters on Cityscape dataset.(1024*2048) > The mIoU is 0.711 after 200 epochs. > But the paper "In Defense...