8000 Tags · dattalab/keypoint-moseq · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Tags: dattalab/keypoint-moseq

Tags

0.6.1

Toggle 0.6.1's commit message
bugfix: pre and post weren't being passed to sample_instances

0.6.0

Toggle 0.6.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #224 from dattalab/dev (Keypoint-MoSeq 0.6.0)

- Brand new calibration widget that relies on fewer dependencies and is therefore more stable.
- Added functions for manually merging similar syllables after modeling.
- Fixed bug where the mice would not be properly aligned in side-view when generating grid movies of 3D keypoints.
- More detailed memory requirements in documentation [here](https://keypoint-moseq.readthedocs.io/en/latest/FAQs.html#out-of-memory)
- 'pre' and 'post' parameters for syllable visualization functions are now defined in seconds rather than frames. FPS for a dataset is now defined in the config file.
- Batch size automatically determined for input data rather than being hard-coded to maximize memory efficiency by minimizing unnecessary zero-padding.
- Noise added to data during preprocessing is now deterministic for easier debugging. 
- Only open a file handle to one video at a time when generating grid movies to avoid max open file handle errors.

0.5.2

Toggle 0.5.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #201 from dattalab/refactor-install

Edited setup.cfg to match jax-moseq's new installation setup. This unpinned a number of libraries and created a version conflict between dynamax and python 3.9, so the Python requirement was also updated to 3.10. Because jax-moseq's installation is now simpler and jax handles CUDA installation automatically, the conda environment yaml files were removed in favor of using pip install keypoint-moseq. Documentation and tutorials were updated to reflect these changes. Finally, black formatting was applied to all files.

2nd attempt - 1st one contained unrelated changed by accident.

0.5.1

Toggle 0.5.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #200 from dattalab/refactor-install

Edited setup.cfg to match jax-moseq's new installation setup. This unpinned a number of libraries and created a version conflict between dynamax and python 3.9, so the Python requirement was also updated to 3.10. Because jax-moseq's installation is now simpler and jax handles CUDA installation automatically, the conda environment yaml files were removed in favor of using pip install keypoint-moseq. Documentation and tutorials were updated to reflect these changes. Finally, black formatting was applied to all files.

0.5.0

Toggle 0.5.0's commit message
Merge branch 'installation_refactor'

0.4.10

Toggle 0.4.10's commit message
additional bugfixes for RTD

0.4.9

Toggle 0.4.9's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #163 from dattalab/sleap_io_hotfix

correct processing of axis order from sleap_io.Labels.numpy()

0.4.8

Toggle 0.4.8's commit message
update paper URL

0.4.7

Toggle 0.4.7's commit message
pin scipy version

0.4.6

Toggle 0.4.6's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #146 from dattalab/better_error_catching

Better error catching + change default iters for apply_model
0