v2.0.2
What's Changed
- support pretrained vit backbone to be safetensor format. by @PPWangyc in #311
- multi-view docs by @themattinthehatt in #326
- Fix multi view model prediction by @Dominic-DallOsto in #328
- Pick best checkpoint by default by @hummuscience in #283
- Add ckpt_path_from_base_path unit tests by @ksikka in #329
- Add full CLI documentation using sphinx-argparse by @ksikka in #330
- DINOv2 and DINOv3 by @themattinthehatt in #338
- pretrained MAE checkpoint for MVT by @themattinthehatt in #339
- fix safetensor ckpt loading by @themattinthehatt in #340
- Pin torch, torchvision, lightning. convert crlf to lf by @ksikka in #344
- MVT+DINOv2 arg fix by @themattinthehatt in #346
- Add inference, training progress tracking for the app by @ksikka in #347
Full Changelog: v2.0.1...v2.0.2