Real-time YOLO image classification
Assign the right label to every image with Ultralytics YOLO26 classification models. Train on your own categories in minutes and run inference in real time on edge, cloud, and mobile hardware.
YOLO26 classification models
YOLO26-cls models assign whole-image labels with top-1 and top-5 accuracy reported below. They are the smallest and fastest members of the family — the nano classifier runs in a few milliseconds on CPU — and they fine-tune on custom categories from a simple folder-per-class dataset.
pip install ultralyticsfrom ultralytics import YOLO
# Load a YOLO26 classification model
model = YOLO("yolo26n-cls.pt")
# Run inference
results = model("image.jpg")| Model | Size (px) | Top-1 acc | Top-5 acc | CPU ONNX (ms) | T4 TensorRT (ms) | Params (M) | FLOPs (B) |
|---|---|---|---|---|---|---|---|
| YOLO26n-cls | 224 | 71.4 | 90.1 | 5.0 ± 0.3 | 1.1 ± 0.0 | 2.8 | 0.5 |
| YOLO26s-cls | 224 | 76.0 | 92.9 | 7.9 ± 0.2 | 1.3 ± 0.0 | 6.7 | 1.6 |
| YOLO26m-cls | 224 | 78.1 | 94.2 | 17.2 ± 0.4 | 2.0 ± 0.0 | 11.6 | 4.9 |
| YOLO26l-cls | 224 | 79.0 | 94.6 | 23.2 ± 0.3 | 2.8 ± 0.0 | 14.1 | 6.2 |
| YOLO26x-cls | 224 | 79.9 | 95.0 | 41.4 ± 0.9 | 3.8 ± 0.0 | 29.6 | 13.6 |
YOLO26 classification benchmarks at 224 pixels from the Ultralytics docs.
Trusted by the world's leading organizations
Our models' impact
Streamline processes across industries with our cutting-edge vision AI models. Speed, accuracy and ease-of-use powered by Ultralytics.
The evolution of Ultralytics YOLO models
See how Ultralytics YOLO evolved from the practical YOLOv5 workflow to edge-ready YOLO26 inference.
Label up to 10x faster with smart annotation
Ultralytics Platform gives you the image annotation tool to build high-quality datasets faster. From smart annotation to precise manual editing, these features are designed to reduce image labeling time without sacrificing quality.
- SAM-powered smart annotation: Masks and bounding boxes in one click.
- Full AI task coverage: Detection, instance segmentation, semantic segmentation, classification, pose, OBB.
- Universal format support: Your choice of YOLO, COCO, and more.
- Team review and versioning: Clear collaboration at every step.
Train on the Best GPUs for Less
26 NVIDIA GPUs starting at $0.24/hr — from Ampere to Blackwell. No markup, no minimums, no commitment.
Explore industry solutions
See how teams apply Ultralytics computer vision across production environments.
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Frequently asked questions
Image classification assigns a whole image to one of a set of classes, with a confidence score for each. It is the simplest computer vision task and the right choice when you need to know what an image shows rather than where objects are — for example quality grading, content sorting, or state monitoring. Ultralytics YOLO classification models are small, fast, and easy to fine-tune.
Use classification when a single label per image is enough, and object detection when you need to locate or count objects within the image. Classification models are lighter and faster to train, so they are often the most efficient solution when position does not matter.
Ultralytics YOLO26 classification models are the recommended starting point, with sizes from nano for edge deployment to extra-large for maximum accuracy. All sizes share the same training and deployment workflow as other Ultralytics YOLO tasks.
Organize images into one folder per class and run the Ultralytics library's train mode, or upload your dataset to Ultralytics Platform and train on cloud GPUs without any local setup. Fine-tuning pretrained weights typically reaches strong accuracy with a few hundred images per class.
Export with export mode to ONNX, TensorRT, CoreML, OpenVINO, LiteRT, and other formats. Classification models are the smallest YOLO variants, making them ideal for mobile apps, embedded devices, and high-throughput services.
Build image classification with Ultralytics
Organize data, train YOLO26 classifiers, and deploy them anywhere with Ultralytics Platform.