CoordConv
By uber-research
coord_conv
An evaluation of the approach from the CoordConv Uber paper. (by pfrendl)
CoordConv | coord_conv | |
---|---|---|
1 | 1 | |
209 | 1 | |
0.0% | - | |
10.0 | 10.0 | |
about 3 years ago | over 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | - |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
CoordConv
Posts with mentions or reviews of CoordConv.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-09-28.
-
[R] CoordConv coordinate regression test shows performance degradation when model contains downsampling
Found relevant code at https://github.com/uber-research/coordconv + all code implementations here
coord_conv
Posts with mentions or reviews of coord_conv.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-09-28.
-
[R] CoordConv coordinate regression test shows performance degradation when model contains downsampling
I have created a repository where I do an alternative test for the regression task described in the Uber CoordConv paper. The results indicate that if the model has downsampling in it, CoordConv degrades performance. I assumed that the test as described in the blog post also had downsampling in it, but this is not the case. Unfortunately, this makes the test not very interesting, hence this alternative test.
What are some alternatives?
When comparing CoordConv and coord_conv you can also consider the following projects:
HugsVision - HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision