Date of Release	Jul 06, 2022
Model Type	Object Detection
Architecture	YOLO, CNN
Framework Used	PyTorch
Annotation Format	YOLOv7 PyTorch TXT
Stars on GitHub	7300+

YOLOv7 was released in July 2022 by WongKinYiu and AlexeyAB. It achieves state of the art performance on and are trained to detect the generic 80 classes in the MS COCO dataset for real-time object detection.

There are six versions of the model ranging from the namesake YOLOv7 (fastest, smallest, and least accurate) to the beefy YOLOv7-E6E (slowest, largest, and most accurate).

The differences between the different sizes of the model are:

The image input resolution
The number of anchors
The number of parameters
The number of layers

The evaluation of YOLOv7 models show that they infer faster (x-axis) and with greater accuracy (y-axis) than comparable realtime object detection models. YOLOv7 evaluates in the upper left - faster and more accurate than its peer networks.

Evolution of layer aggregation strategies in YOLOv7

‍

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

Learn about YOLOv8

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

Learn about YOLOv8

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

Learn about YOLOv8

Model Performance

Model	Test Size	AP^test	AP₅₀^test	AP₇₅^test	batch 1 fps	batch 32 average time
YOLOv7	640	51.4%	69.7%	55.9%	161 fps	2.8 ms
YOLOv7-X	640	53.1%	71.2%	57.8%	114 fps	4.3 ms
YOLOv7-W6	1280	54.9%	72.6%	60.1%	84 fps	7.6 ms
YOLOv7-E6	1280	56.0%	73.5%	61.2%	56 fps	12.3 ms
YOLOv7-D6	1280	56.6%	74.0%	61.8%	44 fps	15.0 ms
YOLOv7-E6E	1280	56.8%	74.4%	62.1%	36 fps	18.7 ms

Explore this model on Roboflow

How to Train YOLOv7 on a Custom Dataset

Follow this tutorial to learn how you can train a Yolov7 model with custom data for you next computer vision project.

How to Deploy YOLOv7 to Jetson Nano

We'll be creating a dataset, training a YOLOv7 computer vision model, and deploying it to a Jetson Nano to perform real-time object detection.

YOLOv7 - A breakdown of how it works

In this post, we break down the internals of how YOLOv7 works and the novel research involved in its construction.

Deploy YOLOv7 to production

Roboflow offers a range of SDKs with which you can deploy your model to production.

Deploy YOLOv7 Instance Segmentation to AWS EC2

Deploy YOLOv7 Instance Segmentation Models to GCP

Deploy YOLOv7 Object Detection Models to NVIDIA Jetson

Deploy YOLOv7 Object Detection Models to CPU (Docker)

Deploy YOLOv7 Object Detection Models to Raspberry Pi

YOLOv7 Annotation Format

YOLOv7

uses the

YOLOv7 PyTorch TXT

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

Label data automatically with YOLOv7

You can automatically label a dataset using

YOLOv7

with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use

YOLOv7

to train a computer vision model.

No items found.