YOLOv4 Tiny vs. MobileNet SSD v2: Compared and Contrasted

Models

The tiny and fast version of YOLOv4 - good for training and deployment on limited compute resources, and getting a feel for your dataset

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

Model Type

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

ResNet-D, YOLO

Annotation Format

Instance Segmentation

Framework

Darknet

TensorFlow 1.5

GitHub

GitHub Stars

81+

License

YOLO

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.