Try the Model

Use the widget below to experiment with DEIM. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

DEIM is a training framework for DETR models. The framework strives to enable "faster convergence and improved accuracy" in models.

With regard to performance, the paper abstract notes:

When integrated with RT-DETR and D-FINE, it consistently boosts performance while reducing training time by 50%. Notably, paired with RT-DETRv2, DEIM achieves 53.2% AP in a single day of training on an NVIDIA 4090 GPU. Additionally, DEIM-trained real-time models outperform leading real-time object detectors, with DEIM-D-FINE-L and DEIM-D-FINE-X achieving 54.7% and 56.5% AP at 124 and 78 FPS on an NVIDIA T4 GPU, respectively, without the need for additional data. We believe DEIM sets a new baseline for advancements in real-time object detection.

DEIM License

DEIM

is licensed under a

Apache 2.0

license.

Performance

Deploy a DEIM API

You can use Roboflow Inference to deploy a

DEIM

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with DEIM

You can automatically label a dataset using DEIM 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 DEIM to train a computer vision model.

No items found.