v0.7.0

datalab-to/suryav0.7.0Nov 27, 2024by VikParuchuri

AI Summary

Performance optimizations designed to reduce overhead and improve processing speed.

Key Highlights

Switched from processpool to threadpool
Optimized postprocessing functions
Removed default heatmap passing to reduce memory overhead

Full Release Notes

- New layout model that detects more block types, includes ordering, and performs better
- Remove ordering model
- Refactor internals to use common model definitions and processors
- Add flags for easier compilation

## What's Changed
* Fix detection results being mutated in place by @iammosespaulr in https://github.com/VikParuchuri/surya/pull/236
* Add support for compiled inference by @iammosespaulr in https://github.com/VikParuchuri/surya/pull/237
* Dev by @VikParuchuri in https://github.com/VikParuchuri/surya/pull/243
* Layout2 by @VikParuchuri in https://github.com/VikParuchuri/surya/pull/249
* New layout model by @VikParuchuri in https://github.com/VikParuchuri/surya/pull/252

**Full Changelog**: https://github.com/VikParuchuri/surya/compare/v0.6.13...v0.7.0