- Automatic confidence map sigma scaling by output stride. Addresses quantization issues with integral regression. - Add automatic evaluation after training. - Initial Kalman filter tracking implementation. - Fix tests, minor bugs and comments.
1.0.4a2
Alpha release of 1.0.4.
- Hotfix for CLI use of topdown batching (`sleap-track [...] --topdown.batch_size`)
1.0.4a1
Alpha release of 1.0.4.
- Add optional batching to topdown predictor inference for speed up in certain cases. This can enabled by adding `--topdown.batch_size 32` to the `sleap-track` CLI. - Modified performance logging to report examples/sec and frames/sec separately (e.g., for topdown). - Add version number to GUI title.
1.0.3
Not secure
Minor enhancements: - explicitly require numpy>=1.16 - check for non-nan points when adding predictions - remove empty frames when deleting instances - command to add user instances for all predicted instances
1.0.2
Not secure
Minor improvements: - use "auto" as default crop size in baseline topdown configs - expose early stopping params in GUI