Published January 16, 2021
| Version v1.1.0
Software
Open
PIQA v1.1.0
Description
PIQA now has an official logo and a banner 🎉
⚡️ Improvements
- Update core components to support PyTorch JIT (c8ac2c3c40c293a4e3a1aef52a3de1fcd47928fd)
- Optimize Gaussian blur with separable convolutions (c8ac2c3c40c293a4e3a1aef52a3de1fcd47928fd)
- Simplify some components (ba0733516d3542d8cebbdf8ecfb178ce440127bd, 0b5a85ed5fbf193b2c3fbcf7a295d88614d86585, 785b449c745a78842dbf9da22cb03654ab034c75)
🐛 Bug fixes
- Fix
MDSIautomatic differentiation (f73b13c73fdd01caf319f5042acfcfb9aa36c0fa, c6d924d68af9d914d3a3cd26bbbd114496ad402c)
📝 Documentation
- Add table of available metrics in README
- Refresh the full documentation (types, shapes, etc.)
- Add mathematical definitions in docstrings
⬆️ Dependencies
PIQA 1.1.0 requires PyTorch 1.7.0 or above.
Files
francois-rozet/piqa-v1.1.0.zip
Files
(35.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:4455326fee519c644fc65cd262128380
|
35.9 kB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/francois-rozet/piqa/tree/v1.1.0 (URL)