Update Readme.md, Edit setup.py and minor update #1
+21
−16
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Outdated suggestions cannot be applied.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.
Thank you for Nice work. I waited a long time for the code to be released.
As you said, I looked at readme.md and set up the environment, but there were some errors, so I solved it, and I slightly fixed what I thought was convenience.
First, I've already used the droid slam before, but due to environmental conflicts, I changed the backends function name to g_backends to form the setup.py file, and I changed "src/lib" to "thirdparty/glory_slam/lib" to solve the problem that the file does not set up due to different paths in the setup.py file.
Second, for convenience, we added a variable called image_dir so that the code to call data can be set in the config.yaml file, so that it can be called from dataset.py .
Third, the Readme.md said "gitclone --recursive https://github.com/eriksandstroem/splat-slam-private ", but there was an error that the git did not exist, so I corrected it to "gitclone --recursive https://github.com/eriksandstroem/splat-slam.git ".
and As for the pytorch version 1.12 does not support 11.7, it was modified to 1.13.1, and the latest version will be installed when you install it with the mentioned "conda install pytorch torch-cuda=11.8-c pytorch -c nvidia". So I changed it to "conda install pytorch==1.13.1 torchvision==0.14.1 torchchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -cnVIDIA" to explicitly set the version.