Ultralytics YOLO26 Modes#
Introduction#
Ultralytics YOLO26 is more than an object detection model: the Ultralytics framework covers the full lifecycle of machine learning models, from training and validation to prediction, export, tracking, and benchmarking. Each mode serves a specific purpose in that workflow.
For planned YOLO27 support, see the YOLO27 preview. YOLO27 is coming soon and is not yet available; this guide uses released YOLO26 models.
Watch: Ultralytics Modes Tutorial: Train, Validate, Predict, Export & Benchmark.
Modes at a Glance#
Ultralytics YOLO26 supports the following modes:
- Train mode: Train or fine-tune your model on custom or built-in datasets.
- Val mode: Validate model performance after training.
- Predict mode: Run inference with your model on new images, videos, and streams.
- Export mode: Convert your model to formats ready for model deployment.
- Track mode: Track objects across video frames and live streams in real time.
- Benchmark mode: Analyze the speed and accuracy of your model in diverse deployment environments.
The sections below summarize each mode and link to its full guide.
Train#
Train mode is used for training a YOLO26 model on a custom dataset. In this mode, the model is trained using the specified dataset and hyperparameters. The training process involves optimizing the model's parameters so that it can accurately predict the classes and locations of objects in an image. Training is essential for creating models that can recognize specific objects relevant to your application.
Val#
Val mode is used for validating a YOLO26 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its accuracy and generalization performance. Validation helps identify potential issues like overfitting and provides metrics such as mean Average Precision (mAP) to quantify model performance. Validation results guide hyperparameter tuning and other model improvements.
Predict#
Predict mode is used for making predictions using a trained YOLO26 model on new images or videos. In this mode, the model is loaded from a checkpoint file, and the user can provide images or videos to perform inference. The model identifies and localizes objects in the input media. Predict mode is how you apply your trained model to practical problems.
Export#
Export mode is used for converting a YOLO26 model to formats suitable for deployment across different platforms and devices. This mode transforms your PyTorch model into optimized formats like ONNX, TensorRT, or CoreML, enabling deployment in production environments. Exporting is essential for integrating your model with various software applications or hardware devices, often resulting in significant performance improvements.
Track#
Track mode extends YOLO26's object detection capabilities to track objects across video frames or live streams. This mode is particularly valuable for applications requiring persistent object identification, such as surveillance systems or self-driving cars. It includes six trackers: TrackTrack (default), BoT-SORT, ByteTrack, OC-SORT, Deep OC-SORT, and FastTracker.
Benchmark#
Benchmark mode profiles the speed and accuracy of various export formats for YOLO26. This mode provides comprehensive metrics on model size, accuracy (mAP50-95 for detection, segmentation, pose, and OBB; mIoU for semantic segmentation; delta1 for depth; or accuracy_top1 for classification), and inference time across different formats like ONNX, OpenVINO, and TensorRT. Benchmarking helps you select the optimal export format based on your specific requirements for speed and accuracy in your deployment environment.
FAQ#
Training a custom object detection model with Ultralytics YOLO26 involves using the train mode. You need a dataset formatted in YOLO format, containing images and corresponding annotation files. Use the following command to start the training process:
Examplefrom ultralytics import YOLO # Load a pretrained YOLO model (you can choose n, s, m, l, or x versions) model = YOLO("yolo26n.pt") # Start training on your custom dataset model.train(data="path/to/dataset.yaml", epochs=100, imgsz=640)For more detailed instructions, you can refer to the Ultralytics Train Guide.
Ultralytics YOLO26 uses various metrics during the validation process to assess model performance. These include:
- mAP (mean Average Precision): This evaluates the accuracy of object detection.
- IoU (Intersection over Union): Measures the overlap between predicted and ground truth bounding boxes.
- Precision and Recall: Precision measures the ratio of true positive detections to the total detected positives, while recall measures the ratio of true positive detections to the total actual positives.
You can run the following command to start the validation:
Examplefrom ultralytics import YOLO # Load a pretrained or custom YOLO model model = YOLO("yolo26n.pt") # Run validation on your dataset model.val(data="path/to/validation.yaml")Refer to the Validation Guide for further details.
Ultralytics YOLO26 offers export functionality to convert your trained model into various deployment formats such as ONNX, TensorRT, CoreML, and more. Use the following example to export your model:
Examplefrom ultralytics import YOLO # Load your trained YOLO model model = YOLO("yolo26n.pt") # Export the model to ONNX format (you can specify other formats as needed) model.export(format="onnx")Detailed steps for each export format can be found in the Export Guide.
Benchmark mode in Ultralytics YOLO26 is used to analyze the speed and accuracy of various export formats such as ONNX, TensorRT, and OpenVINO. It provides metrics like model size,
mAP50-95for object detection, and inference time across different hardware setups, helping you choose the most suitable format for your deployment needs.Examplefrom ultralytics.utils.benchmarks import benchmark # Run benchmark on GPU (device 0) # You can adjust parameters like model, dataset, image size, and precision as needed benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=0)For more details, refer to the Benchmark Guide.
Real-time object tracking can be achieved using the track mode in Ultralytics YOLO26. This mode extends object detection capabilities to track objects across video frames or live feeds. Use the following example to enable tracking:
Examplefrom ultralytics import YOLO # Load a pretrained YOLO model model = YOLO("yolo26n.pt") # Start tracking objects in a video # You can also use live video streams or webcam input model.track(source="path/to/video.mp4")For in-depth instructions, visit the Track Guide.