Open XianLi1214 opened 3 years ago
It would certainly be possible by just stacking the multiple images in the channels dimension, e.g. instead of and RGB image having 3 channels you could pack 2x RGB images from sequential frames into 6 channels. You'd have to prepare the data appropriately. Clearly the number of images you could pack together in this manner would be dictated by the GPU memory you have available for training.
when i use the code and i want to install the datasets i faced on this error: Downloading facades dataset...Error using websave (line 98) Could not access server. http=127.0.0.1.
Error in p2p.util.downloadFacades (line 29) websave(tempZipFile, dataUrl);
Sounds like maybe there is an issue with your connection? You could try looking in that file and downloading the facades dataset (the url is in there) and then running the post processing steps manually.
Is it possible to use multiple images as input for this code? The temporal information between images are needed in my work, thanks in advance.