OpenMMLab Vision Models

Compare both OpenMMLab vision models we track, all of them open-weight.

2 models · 2 open-weight · Updated Dec 2022

About OpenMMLab Vision Models

Every OpenMMLab vision model in our catalog is open-weight. Both publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on GPL v3 and MIT licenses. The newest additions are RTMDet (Dec 2022) and Co-DETR (Nov 2022).

The OpenMMLab models we list cover object detection (2 models). For object detection, start with RTMDet or Co-DETR.

On the open-weight tier, Co-DETR is the largest at 304M parameters and RTMDet the smallest at 4.8M-94.9M, small enough to run on a single GPU or on-device. 1 of the 2 open OpenMMLab models carry a permissive license, so commercial use is straightforward; the other 1 ship under terms worth reading before you deploy.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which OpenMMLab Model Should You Use?

What each of the 2 OpenMMLab vision models in our catalog is built for, and how you run it.

RTMDet: Best for: Object Detection. Open weights: GPL v3 license, 4.8M-94.9M parameters. Self-host it or run it here. Small enough for on-device and edge deployment.
Co-DETR: Best for: Object Detection. Open weights: MIT license, 304M parameters. Self-host it or run it here. Small enough for on-device and edge deployment.

Open-Source OpenMMLab Models

2 models with downloadable weights you can self-host under their licenses (GPL v3 and MIT).

RTMDet

RTMDet is a real-time object detection model developed by OpenMMLab, released in December 2022 under the GPL-3.0 license. It adopts a single-stage detection architecture with large-kernel depthwise convolution in both the backbone and neck, enabling it to capture long-range spatial dependencies without the computational cost of full self-attention. The model family spans from RTMDet-tiny to RTMDet-x, covering a wide range of speed-accuracy operating points.RTMDet-x achieves 52.6% AP on COCO at 114 FPS on an NVIDIA 3090 GPU. The architecture supports instance segmentation and rotated object detection variants. RTMDet is included in the OpenMMLab ecosystem and is well suited for applications requiring fast, accurate detection with flexible model sizing.

Co-DETR

Co-DETR (Co-Deformable-DETR) is an object detection model developed by researchers at Sense-X and OpenMMLab, released in November 2022. It improves upon standard DETR-based detectors by introducing a collaborative hybrid assignment training scheme that enables the encoder to learn from multiple auxiliary heads simultaneously, alongside the primary one-to-one assignment used during inference. This auxiliary supervision significantly accelerates convergence and improves overall detection accuracy without adding inference cost.Co-DETR is evaluated on the COCO benchmark, where it achieves 59.5% AP when applied to DINO-Deformable-DETR with a Swin-L backbone. With a ViT-L backbone it reaches 66.0% AP on COCO test-dev, outperforming prior methods at comparable model scales. It is suitable for high-accuracy object detection tasks where training efficiency and peak performance on standard benchmarks are priorities.

Frequently Asked Questions About OpenMMLab Vision Models

Which OpenMMLab models can do object detection?

2 of the 2 OpenMMLab vision models we track handle object detection: RTMDet and Co-DETR. Each model page lists its full task coverage, license, and specs.

Are OpenMMLab vision models open source?

Yes. Both OpenMMLab vision models we track publish downloadable weights you can self-host under their licenses (GPL v3 and MIT).

What is the best OpenMMLab model for object detection?

We do not publish an OpenMMLab-only ranking, so pick on constraints rather than a label. 2 OpenMMLab models handle object detection; the most recent is RTMDet (Dec 2022). Measured scores across every lab we test are on our object detection benchmark, linked at the bottom of this page. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model.

How many OpenMMLab vision models are on Roboflow Playground?

We track 2 live OpenMMLab vision models. The most recent addition is RTMDet, released Dec 2022.

This page lists both OpenMMLab vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover object detection, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.