Models

What is MT-YOLOv6?

MT-YOLOv6 is a YOLO based model released in 2022.

About the model

Here is an overview of the

MT-YOLOv6

model:

Date of Release Jun 23, 2022
Model Type Object Detection
Architecture CNN, YOLO
Framework Used PyTorch
Annotation Format meituan/yolov6
Stars on GitHub 4400+

The YOLOv6 repository was published June 2022 by Meituan, and it claims new state-of-the-art performance on the COCO dataset benchmark. We'll leave it to the community to determine if this name is the best representation for the architecture.

https://blog.roboflow.com/yolov6/

In any case, it's clear MT-YOLOv6 (hereafter YOLOv6 for brevity) is popular. In a couple short weeks, the repo has attracted over 2,000+ stars and 300+ forks.

YOLOv6 claims to set a new state-of-the-art performance on the COCO dataset benchmark. As the authors detail, YOLOv6-s achieves 43.1 mAP on COCO val2017 dataset (with 520 FPS on T4 using TensorRT FP16 for bs32 inference).

(For point of comparison, YOLOv5-s achieves 37.4 mAP @ 0.95% on the same COCO benchmark.)
The YOLOv6 repository authors published the below evaluation graphic, demonstrating YOLOv6 outperforming YOLOv5 and YOLOX at similar sizes.

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Model Performance

Model Size mAPval
0.5:0.95
SpeedT4
trt fp16 b1
(fps)
SpeedT4
trt fp16 b32
(fps)
Params
(M)
FLOPs
(G)
YOLOv6-N 640 35.9300e
36.3400e
802 1234 4.3 11.1
YOLOv6-T 640 40.3300e
41.1400e
449 659 15.0 36.7
YOLOv6-S 640 43.5300e
43.8400e
358 495 17.2 44.2
YOLOv6-M 640 49.5 179 233 34.3 82.2
YOLOv6-L-ReLU 640 51.7 113 149 58.5 144.0
YOLOv6-L 640 52.5 98 121 58.5 144.0

Explore this model on Roboflow

No items found.

MT-YOLOv6 Annotation Format

MT-YOLOv6

uses the

meituan/yolov6

annotation format. If your annotation is in a different format, you can use Roboflow's annotation conversion tools to get your data into the right format.

Convert data between formats

Deploy a computer vision model today

Join 100k developers curating high quality datasets and deploying better models with Roboflow.

Get started