v2.0.6

What's Changed

• 3d reprojection heatmap loss by @themattinthehatt in #363
• README changes by @ksikka in #364
• Migration guide, new reference docs by @ksikka in #365
• Fix a broken docs link, add a migration from CLI example by @ksikka in #366
• skip tests that require figshare downloads by @themattinthehatt in #367
• Replace figshare with github releases by @ksikka in #368
• deprecation warning for old inference scripts by @themattinthehatt in #370
• handle gated repo error by @themattinthehatt in #369
• Add some docstrings about cropzoom methods by @ksikka in #371
• Docs: cpu-only app install, add/transfer existing project, github, discord, app release notes by @ksikka in #373
• Add docs for unlabeled file changes by @ksikka in #377
• Fix double loss weighting by applying weights only in LossFactory by @twheatcroft07 in #376

New Contributors

• @twheatcroft07 made their first contribution in #376

Full Changelog: v2.0.5...v2.0.6

v2.0.5

FIRST OFFICIAL RELEASE FOR APP VERSION 2.0

What's Changed

• Fix: obey eval.test_videos_directory in multiview post-training logic by @ksikka in #359
• [PREVIEW] New docs by @ksikka in #360

Full Changelog: v2.0.4...v2.0.5

v2.0.4

What's Changed

• fix NaN gradients in 3d triangulation loss by @themattinthehatt in #358

Full Changelog: v2.0.3...v2.0.4

v2.0.3

What's Changed

• linter workflow by @themattinthehatt in #348
• properly handle 3D augmentations with <3 points by @themattinthehatt in #350
• Refactor state dict loading in vits.py by @PPWangyc in #352
• fix nan-handling in pairwise projection loss by @themattinthehatt in #354
• remove auto-generated api docs by @themattinthehatt in #355
• remove streamlit apps by @themattinthehatt in #357

Full Changelog: v2.0.2...v2.0.3

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

v2.0.1

What's Changed

• dependency version updates by @themattinthehatt in #324

Full Changelog: v2.0.0...v2.0.1

v2.0.0

What's Changed

• multi-view transformers by @themattinthehatt @LennyAharon @ksikka in #323

Full Changelog: v1.9.2...v2.0.0

v1.9.2

What's Changed

• Mention SLEAP to lightning pose conversion in docs by @Dominic-DallOsto in #306
• keep lists longer than 2 as lists by @hummuscience in #296
• Remove unexpected save_heatmaps parameter predict_new_vids.py by @hummuscience in #307
• Pin transformers version by @ksikka in #310
• Calibration plot for frame diagnostics streamlit by @hummuscience in #308
• Fix checkpoint compatibility for upsampling_layers by @hummuscience in #314
• flake by @themattinthehatt in #316

New Contributors

• @Dominic-DallOsto made their first contribution in #306

Full Changelog: v1.9.1...v1.9.2

v1.9.1

What's Changed

• load pytorch ckpt files for pretrained vits by @themattinthehatt in #304
• pypi release workflow by @themattinthehatt in #305

Full Changelog: v1.9.0...v1.9.1

v1.9.0

What's Changed

• update colab notebook by @themattinthehatt in #292
• remove unnecessary jupyter notebook data by @themattinthehatt in #293
• remove neck in vits to avoid over stacking issues by @PPWangyc in #275
• fix vit_b_sam predict model init issue by @PPWangyc in #294
• Add a hidden run_app command by @ksikka in #298
• typecheck fix by @themattinthehatt in #300
• implement SAM backbone with huggingface transformers package by @themattinthehatt in #301
• new backbone: ViT pretrained on imagenet with mae loss by @themattinthehatt in #302
• pretrained dino backbone by @themattinthehatt in #303

New Contributors

• @PPWangyc made their first contribution in #275

Full Changelog: v1.8.1...v1.9.0