-
Notifications
You must be signed in to change notification settings - Fork 7.1k
Added ETH3D stereo dataset #6349
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @TeodorPoncu , minor comments but LGTM anyway
disparity_map = np.abs(disparity_map) # ensure that the disparity is positive | ||
mask_path = Path(file_path).parent / "mask0nocc.png" | ||
valid_mask = Image.open(mask_path) | ||
valid_mask = np.asarray(valid_mask).astype(np.bool_) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I was surprised by the us of np.bool_
and looking at numpy's warning, I think this should just be the buildin bool
https://numpy.org/devdocs/release/1.20.0-notes.html#using-the-aliases-of-builtin-types-like-np-int-is-deprecated
test/test_datasets.py
Outdated
assert dataset._images and len(dataset._images) == len( | ||
dataset._disparities | ||
), "Training images do not match with training disparities" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Curious why we need this assertion. Isn't it taken care of in the shape_test_...
call below?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
That assertion is unnecessary indeed! Thanks!
Summary: * Added ETH3D stereo dataset * Small doc-reformating * Removed assertions with no use, changed np conversion * Added ETH3D stereo dataset * Removed assertions with no use, changed np conversion * rebased on main * Revert "Removed assertions with no use, changed np conversion" This reverts commit 1478a8c. * Update to np.bool instead of np.bool_ * lint and mypy nit fix * test nit Reviewed By: datumbox Differential Revision: D39013683 fbshipit-source-id: adf03910e184c63363c5398c171ac668e1b8b3a9
This is a continuation of the PR split (#6311, #6269) which contains the ETH3D low-res two-view dataset.