Megvii Vision Models

Compare the one Megvii vision model we track, all of them open-weight.

1 model · 1 open-weight · Updated Jul 2021

About Megvii Vision Models

Every Megvii vision model in our catalog is open-weight. The one model we track publishes downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on Apache 2.0 terms. The most recent release is YOLOX (Jul 2021).

The Megvii models we list cover object detection (1 model).

On the open-weight tier, YOLOX runs at 0.91M-99.1M parameters.

Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which Megvii Model Should You Use?

The one Megvii vision model in our catalog and what it is built for.

YOLOX: Best for: Object Detection. Open weights: Apache 2.0 license, 0.91M-99.1M parameters. Self-host it or run it here. Small enough for on-device and edge deployment.

Open-Source Megvii Models

1 model with downloadable weights you can self-host under their licenses (Apache 2.0).

YOLOX

YOLOX is an anchor-free object detection model developed by Megvii (Face++), released in July 2021 under the Apache 2.0 license. It applies anchor-free detection to the YOLO framework, decoupling the classification and regression heads to allow each to optimize independently, and introduces the SimOTA label assignment strategy for improved training convergence. YOLOX achieves strong accuracy-speed tradeoffs and outperforms YOLOv5 on COCO at comparable model sizes.YOLOX-L achieves 50.0% AP on COCO at 68.9 FPS on an NVIDIA V100 GPU. The model is available in a range of sizes from YOLOX-Nano to YOLOX-X and supports deployment through ONNX, TensorRT, and other standard export formats. It is suitable for real-time object detection applications and has been widely adopted in industrial and research detection pipelines.

Frequently Asked Questions About Megvii Vision Models

Which Megvii models can do object detection?

1 of the 1 Megvii vision models we track handles object detection: YOLOX. Each model page lists its full task coverage, license, and specs.

Are Megvii vision models open source?

Yes. The one Megvii vision model we track publishes downloadable weights you can self-host under its license (Apache 2.0).

How many Megvii vision models are on Roboflow Playground?

We track 1 live Megvii vision model. The most recent addition is YOLOX, released Jul 2021.

This page lists the one Megvii vision model 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.