How to label data for YOLO26 training
Before you can train a computer vision model, you need labeled data on which to train your model. The more accurate the labels, or annotations, are, the higher the performance the model will achieve.
Overview
This guide shows how to label images for YOLO26 with Roboflow Annotate, then train YOLO26 in Roboflow or export your labels to train it yourself.
Roboflow Annotate runs in your browser and is free to start. Roboflow is SOC 2 Type 2 compliant and used by over 2 million developers.
To label data for YOLO26, you will:
- Create an object detection project and upload images
- Open an image in Roboflow Annotate
- Draw bounding boxes
- Label faster with AI
- Train YOLO26 or export your data
Step 1: Create a project and upload images
Create a free Roboflow account, then create a new project. Give it a name and choose Object Detection as the project type:

Next, upload your images. Drag them onto the Upload Data page, or select files or a whole folder. If you already have labels, upload the annotation files with your images to review or fix them in Roboflow Annotate:

Step 2: Open an image
Click any image in your project to open it in Roboflow Annotate:

Your project's classes are listed on the left. The labeling tools are in the toolbar on the right: bounding boxes, polygons, the brush, and the AI labeling tools.
Step 3: Draw bounding boxes
Select the bounding box tool, or press B, and drag a box around each object. Then pick its class from the list, or type a new class name:

Draw each box tight to the edges of the object, so YOLO26 learns exactly where the object starts and ends. Our labeling best practices cover more tips.
You can also draw polygons (press P) in an object detection project. Roboflow converts them to boxes for training, and polygons can improve accuracy.
Step 4: Label faster with AI
Smart Polygon (opens in a new tab) outlines an object from a single click, using Segment Anything. Press S, click the object, and adjust the outline if needed:

With Box Prompting (opens in a new tab), you label one example of a class and Roboflow suggests boxes around the similar objects in the image. Its suggestions improve with each image you label:

Label Assist (opens in a new tab) suggests boxes from a model: one trained on the 80 COCO classes, a public model from Roboflow Universe (opens in a new tab), or an earlier version of your own. To label a whole batch at once, use Auto Label: name your classes, a foundation model labels every image, and you review the results.
Step 5: Train YOLO26 or export your data
When your images are labeled, generate a dataset version. Then open Train in your project, click "Custom Training", and choose "YOLO26". The Train a Model guide (opens in a new tab) walks through each option.
To train YOLO26 on your own hardware instead, export the version as YOLO26, one of the formats Roboflow exports.
Learn how to label data for other models
Each guide walks through the same steps in Roboflow Annotate for a different model.
- Detectron2 Instance Segmentation
- Detectron2 Object Detection
- DETR
- Florence-2
- GPT-4o
- MMDetection
- MT-YOLOv6
- PaliGemma
- RF-DETR
- RF-DETR Pose
- RF-DETR Segmentation
- RF-DETR Semantic Segmentation
- RTMDet
- Vision Transformer
- YOLO-NAS
- YOLO11
- YOLO11 OBB
- YOLOR
- YOLOS
- YOLOv3 PyTorch
- YOLOv4 PyTorch
- YOLOv5
- YOLOv5 Classification
- YOLOv5 Instance Segmentation
- YOLOv7
- YOLOv7 Instance Segmentation
- YOLOv8
- YOLOv8 Classification
- YOLOv8 Instance Segmentation
- YOLOv8 Oriented Bounding Boxes
- YOLOv9
- YOLOv10
- YOLOv12
- YOLOX