Grégoire Payen de La Garanderie

Hi @yuniw18 I haven’t had time to have a close look but what you say sounds right. Sorry about that.

Hello. Would it be possible that you share more details of what you are trying to do?

The only difficulty that I can think of is that you need to permute your feature maps to be of shape (batch_size, w, h, channel) before the pooling layer because...

No, I think that (b, w, h, c) should work. Just make sure that “c” is last. That’s because the FFT works on the last dimension.

Thanks @ziqiangchen . That's right, input_size should be 3.

Hi, that’s a bit strange. The values are completely off. I’ll try to replicate your results. It sounds like a scaling issue or a disparity/depth mismatch. When calling the evaluation...

Yes, sorry for the confusion. You are right. This is the disparity value however this might not have be the best definition of disparity. I will try to update the...

The paper is correct however, when I released this code, I tried to clean up the code but the definition in the code doesn’t match the paper anymore. The above...

I think that the problem is that the tan(b(1)) is the ratio x/z, not x itself. If you can assume z=1 which is the case when reprojecting rectilinear images it...

The code that you are refering to is related to the object detection network, not the depth estimation so it is not relevant. `targets_r=depth` should be right for your use...