v1.16.3

v1.16.3 (2025-01-27)

Build System

• Updated poetry lock (b9a04e6)

Performance Improvements

• Bump sahi to support YOLOv11 (d36b494)

---

Detailed Changes: v1.16.2...v1.16.3

v1.16.2

v1.16.2 (2025-01-14)

Performance Improvements

• Better handling of cuda devices by id across both detection and clustering commands with --device cuda:0 (ae8e395)

---

Detailed Changes: v1.16.1...v1.16.2

v1.16.1

v1.16.1 (2025-01-13)

Bug Fixes

• Correct argument order to create_model and added types for float/int args in detect (6bb93bb)

---

Detailed Changes: v1.16.0...v1.16.1

v1.16.0

v1.16.0 (2025-01-11)

Features

• Added support for auto-detecting detection model types from huggingface and loading models from a directory. If models do not have the model type encoded in the name, e.g. yolov5 the --model-type yolov5 must be used (3ea7612)

---

Detailed Changes: v1.15.0...v1.16.0

v1.15.0

v1.15.0 (2025-01-10)

Features

• Add second score and class assignment for roi cluster (8412941)

---

Detailed Changes: v1.14.2...v1.15.0

v1.14.2

v1.14.2 (2025-01-10)

Bug Fixes

• Copy rois to crop path to avoid removal (00ca30f)

Performance Improvements

• Remove only dark and blurry (1e0de1f)

---

Detailed Changes: v1.14.1...v1.14.2

v1.14.1

v1.14.1 (2024-12-07)

Bug Fixes

• Correct clean_vision for roi and added check for is_low_information_issue and is_near_duplicates_issue (849d432)

---

Detailed Changes: v1.14.0...v1.14.1

v1.14.0

v1.14.0 (2024-11-27)

Features

• Remove dark and blurry examples in clustering using cleanvision (c04fab7)

v1.13.2

v1.13.2 (2024-11-23)

Bug Fixes

• Correct vits assignment (d35ae96)

v1.13.1

v1.13.1 (2024-11-23)

Bug Fixes

• Handle index out of range on vits assign (2aee31a)

Refactoring

• Rename vits prediction option to --use-vits (a1e1301)