Product
Solutions
Resources
Pricing
Docs
Book a demoSign in
Models
Object Detection
DETR

Explore Models

By Task
All Models (32)Object Detection Models (19)Classification Models (7)Instance Segmentation Models (3)Semantic Segmentation Models (1)
By Feature
Optimal for Edge Deployment
Compare to related models

What is DETR?

Detection Transformer (DETR) is an end-to-end object detection model implemented using the Transformer architecture.

How to Train
DETR
DETR
Training Notebook
View on GitHub
DETR
Video Guide
DETR

Training on Kaggle
DETR

Training on SageMaker

About the model

Here is an overview of the

DETR

model:
‍

Date of Release
Model Type Object Detection
Architecture Transformers
Framework Used PyTorch
Annotation Format COCO JSON
Stars on GitHub 10700+

Detection Transformer (DETR) is an end-to-end object detection model implemented using the Transformer architecture. DETR was developed by Facebook Research. The baseline DETR model has an AP score of 42.0% on COCO.

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

name backbone schedule inf_time box AP url size
0 DETR R50 500 0.036 42.0 model | logs 159Mb
1 DETR-DC5 R50 500 0.083 43.3 model | logs 159Mb
2 DETR R101 500 0.050 43.5 model | logs 232Mb
3 DETR-DC5 R101 500 0.097 44.9 model | logs 232Mb

Explore this model on Roboflow

How to Train Object Detection Transformer on Custom Dataset

In this tutorial, we'll show you how to train Object Detection Transformers using DETR.

Video
Blog

DETR Annotation Format

DETR

uses the

COCO JSON

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

Compare to related models

Curious about how YOLOv5 compares to other models? Check out our model comparisons.

No items found.

Deploy a computer vision model today

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

Get started