zhuixunforever

By the way, do you undistorts the images when you train or test? In eval.py, it seems to call 'centre' instead of 'centre_processed' that is undistorted images. And when I...

@whubaichuan in your paper, "During the testing phase, the resolution of input image is 1600 × 1200". in other words, you use 400*296 depth map to evaluate, and get table3...

@masoudpz hai, have you successed? where to clone your version?

I'll try it, thank you very much!

how did you compile ./utils/build.py on windows?? just run ./make.sh??? @masoudpz

that's all right! thanks

I have meet the same question in other project, and find this issue. But change 'shuffle=False' in and change 'torch\utils\data\sampler.py' is not what I want. Then I find the source...

@monisha21898 In my project, I use ' torch.set_default_tensor_type('torch.cuda.FloatTensor')', and when I delete it , my problem get solved. The generator is created in cpu, and the device of return value...

You may need to debug, see the device of 'n','generator', and the current device of your project. This should not be wrong if all three are the same

have you solve this problem, I meet the same issue.