PengWang
> he froze batch norm during training. So the synchronized batch norm does not work in the code? Since sync bn should improve the performance, rather than decrease it
It is still under collection. Will get back once we obtain them. We may not have the ground truth depth every pixel, but will have stereo pairs for each image.
In current data we already released, we do not have snow/rain situation, only night situations are available. We need to have the images labelled in rain/snow situations, we will release...
Is this due to the version of you lib in opengl is not compatible with that used in our case? ``` bash glxinfo | grep "OpenGL version" ``` we have...
It seems init GLEW is not necessary for successfully render a depth map. I have already update to rm the line of ERROR message. You may check it out again.
Is it possible due to some driver conflict ? Try to reinstall nvidia driver (I met segment fault when having matlab or nouveau driver)
@stevenwudi From those examples I think you got every thing right. How about the first image you showed with misalignment, is it the same with the example in the demo...
> I'm trying to use proj_point_cloud.py in self_localization but I'm getting the same "Failed to initialize GLEW" problem. You mention that I should be able to generate a depth image...
> Some of my label pngs are broken too @pengwangucla. I hope you fix this soon. Thank you for the great dataset! Leave Baidu and have no access to maintain...
from my observation of the horizontal line, 000 should be -10 and 010 is 0 elevation ?