Context-Enhanced-Stereo-Transformer

Context-Enhanced-Stereo-Transformer copied to clipboard

about M1,M2,M3 in Context Enhanced Path (CEP)

1

Hello, I read your code,It seems that the code does not reflect three different design choices for Context Enhanced Path (CEP).all the feat use one Transformer with same architecture of...

xubin1994

RuntimeError: stack expects each tensor to be equal size, but got [3, 390, 771] at entry 0 and [3, 371, 880] at entry 1

1

batch size = 2 will cause this ,when batch size =1 ,it can run

CHXAdmin

About the generalization experiment.

2

Hi, Thanks a lot for your great work. It can be seen from your paper that you are aiming to enhance the generalization ability of the model, but there is...

Zhaohuai-L

Your work is truly impressive! I have a question regarding the SceneFlow dataset subset that I would like to inquire about. I've noticed that the directory structure after extracting the...

xgyutu

About model parallel

2

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1! (when checking argument for argument weight in method wrapper__cudnn_convolution)

CHXAdmin