MobileNet SSD v2 vs. YOLOS

Both MobileNet SSD v2 and YOLOS are commonly used in computer vision projects. Below, we compare and contrast MobileNet SSD v2 and YOLOS.

Models

This architecture provides good realtime results on limited compute. It's designed to run in realtime (30 frames per second) even on mobile devices.

YOLOS looks at patches of an image to to form "patch tokens", which are used in place of the traditional wordpiece tokens in NLP.

Model Type

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

Transformer, YOLO

Frameworks

TensorFlow 1.5

PyTorch

Annotation Format

Instance Segmentation

GitHub

GitHub Stars

81+

812+

License

MIT

Paper

Training Notebook

Deploy Model

Provide your own image below to test YOLOv8 and YOLOv9 model checkpoints trained on the Microsoft COCO dataset.

COCO can detect 80 common objects, including cats, cell phones, and cars.