# \#machine-learning
**URL:** https://www.robotexchange.io/tag/machine-learning/27.md
[Latest](https://www.robotexchange.io/latest.md) · [Categories](https://www.robotexchange.io/categories.md) · [Tags](https://www.robotexchange.io/tags.md)
---
## [How to plan a basic vision-based quality control system](https://www.robotexchange.io/t/how-to-plan-a-basic-vision-based-quality-control-system/4748)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:18am UTC](https://www.robotexchange.io/t/how-to-plan-a-basic-vision-based-quality-control-system/4748 "2026-09-02T00:18:57Z")
Based on contributions by anarueda. Before writing any detection code, it helps to plan a vision-based quality control (QC) system as a sequence of well-defined stages. This how-to is a workflow overview, not a specific…
---
## [How to segment objects with SAM 3 using text prompts in Python](https://www.robotexchange.io/t/how-to-segment-objects-with-sam-3-using-text-prompts-in-python/4747)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:18am UTC](https://www.robotexchange.io/t/how-to-segment-objects-with-sam-3-using-text-prompts-in-python/4747 "2026-09-02T00:18:55Z")
Based on contributions by Tim. SAM 3 is Meta’s open-vocabulary segmentation model. Instead of clicking on an object or drawing a bounding box, you describe what you’re looking for in plain text, "red cylinder", "gripper…
---
## [How to augment images and OBB labels to expand a YOLO training set](https://www.robotexchange.io/t/how-to-augment-images-and-obb-labels-to-expand-a-yolo-training-set/4704)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:17am UTC](https://www.robotexchange.io/t/how-to-augment-images-and-obb-labels-to-expand-a-yolo-training-set/4704 "2026-09-02T00:17:13Z")
Based on contributions by Luckyhipster10, Mathijs. If you don’t have enough hand-annotated images for a good oriented bounding box (OBB) model, you can generate extra training images by applying random transformations (…
---
## [How to train a YOLO OBB model and get the center and angle of detections](https://www.robotexchange.io/t/how-to-train-a-yolo-obb-model-and-get-the-center-and-angle-of-detections/4702)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:17am UTC](https://www.robotexchange.io/t/how-to-train-a-yolo-obb-model-and-get-the-center-and-angle-of-detections/4702 "2026-09-02T00:17:08Z")
Based on contributions by sarahstam, 20129556. A regular YOLO bounding box is always axis-aligned, so it can’t tell you how an object is rotated. An oriented bounding box (OBB) model fits a rotated rectangle to each obj…
---
## [How to train a YOLO object detection model with Roboflow and Ultralytics](https://www.robotexchange.io/t/how-to-train-a-yolo-object-detection-model-with-roboflow-and-ultralytics/4700)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:17am UTC](https://www.robotexchange.io/t/how-to-train-a-yolo-object-detection-model-with-roboflow-and-ultralytics/4700 "2026-09-02T00:17:03Z")
Based on contributions by StevenVanDerGaag, Mathijs, aashish. Once you have an annotated dataset (see How to annotate and label images in Roboflow for YOLO training), you can train your own YOLO model with the Ultralyti…
---
## [How to annotate and label images in Roboflow for YOLO training](https://www.robotexchange.io/t/how-to-annotate-and-label-images-in-roboflow-for-yolo-training/4699)
**Author:** [@thijs](https://www.robotexchange.io/u/thijs)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 12:17am UTC](https://www.robotexchange.io/t/how-to-annotate-and-label-images-in-roboflow-for-yolo-training/4699 "2026-09-02T00:17:00Z")
Based on contributions by Mark.jensen, Rafika. Before you can train a YOLO model you need a labelled image dataset: a set of images with a box (or polygon) drawn around every object you want to detect. Roboflow is a fre…