Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

multiple images as inputs #15

Open
XianLi1214 opened this issue Jun 4, 2021 · 3 comments
Open

multiple images as inputs #15

XianLi1214 opened this issue Jun 4, 2021 · 3 comments

Comments

@XianLi1214
Copy link

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.

@justinpinkney
Copy link
Collaborator

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.

@mehrnooshkarimi
Copy link

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);

@justinpinkney
Copy link
Collaborator

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants