feat: add rgbd representation of 3d mesh#753
Merged
Conversation
Codecov ReportBase: 88.13% // Head: 87.90% // Decreases project coverage by
Additional details and impacted files@@ Coverage Diff @@
## main #753 +/- ##
==========================================
- Coverage 88.13% 87.90% -0.23%
==========================================
Files 133 133
Lines 6703 6741 +38
==========================================
+ Hits 5908 5926 +18
- Misses 795 815 +20
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report at Codecov. |
f33d39b to
4e83370
Compare
4e83370 to
eca47f6
Compare
eca47f6 to
783f31e
Compare
783f31e to
9b564e7
Compare
Co-authored-by: Alex Cureton-Griffiths <[email protected]> Signed-off-by: anna-charlotte <[email protected]>
Co-authored-by: Alex Cureton-Griffiths <[email protected]> Signed-off-by: anna-charlotte <[email protected]>
Signed-off-by: anna-charlotte <[email protected]>
1c76b10 to
7b609fc
Compare
added 3 commits
November 15, 2022 15:32
|
📝 Docs are deployed on https://ft-feat-add-rgbd-representation-751--jina-docs.netlify.app 🎉 |
1 similar comment
|
📝 Docs are deployed on https://ft-feat-add-rgbd-representation-751--jina-docs.netlify.app 🎉 |
Signed-off-by: anna-charlotte <[email protected]>
|
📝 Docs are deployed on https://ft-feat-add-rgbd-representation-751--jina-docs.netlify.app 🎉 |
Signed-off-by: anna-charlotte <[email protected]>
f6b9bc8 to
7da86f2
Compare
|
📝 Docs are deployed on https://ft-feat-add-rgbd-representation-751--jina-docs.netlify.app 🎉 |
samsja
approved these changes
Nov 17, 2022
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Goals:
A common input format of 3d data for machine learning model are RGBD images due to the fixed size ndarray representation. RGB-D images are usually stored in 2 separate image files, the first one stores the RGB values (shape=(n, m, 3)), the second one stores a depth value for each pixel of the RGB image (shape=(n, m, 1)). Those two ndarray can be concatenated to one ndarray of shape=(n, m, 4).
Representation in DocArray:
Save the two file paths in the
.uriattribute of a Documents.chunksLoad the 2 files into 1 tensor and store the tensor of shape=(n, m, 4) in the Document's top level
.tensorattribute.load chunks uris to top level rgbd image tensor
add
.display()function for rgbd image tensorcheck and update documentation, if required. See guide