RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[32, 256, 192, 3] to have 3 channels, but got 256 channels instead

[genius9527]

Hello, I downloaded your code and configured the environment according to the guide.But when I was training, I encountered the following problem：

RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[32, 256, 192, 3] to have 3 channels, but got 256 channels instead

I wonder if this is an environmental issue, and my environment is as follows：
ubuntu 18.04.3
python 3.6.9
nvidia 390.129
cuda 9.0.176
cudnn 7.0.5
pytorch 1.0.0
torchvision 0.1.6
tensorboardX 1.6.0

Looking forward to your reply。

[genius9527]

My gosh i solved it, thank you all。

I reinstalled the system several times, and in the end I found that the torchvision and torch version correspond to the problem.

now my environment is as follows：
ubuntu 16.04.1
python 3.6.4
nvidia 410.78
cuda 10.0
cudnn 7.4.2
pytorch 1.0.0
torchvision 0.2.1
tensorboardX 1.6.0

pytorch 1.0.0 and torchvision 0.2.1 corresponding。