Navigate:
~$YOLOX0.1%

YOLOX: Anchor-free object detection model

PyTorch anchor-free object detector with scalable model variants.

LIVE RANKINGS • 01:42 PM • STEADY
OVERALL
#352
1
AI & ML
#97
2
30 DAY RANKING TREND
ovr#352
·AI#97
STARS
10.3K
FORKS
2.4K
7D STARS
+12
7D FORKS
+5
Tags:
See Repo:
Share:

Learn more about YOLOX

YOLOX is an object detection model that removes the anchor-based detection mechanism used in earlier YOLO versions, replacing it with an anchor-free approach. The architecture is implemented in PyTorch with a companion MegEngine implementation available separately. The model family includes variants ranging from YOLOX-Nano with 0.91M parameters to YOLOX-X with 99.1M parameters, enabling deployment across different computational constraints. Common applications include real-time object detection in computer vision pipelines, with support for edge deployment through quantization and conversion to optimized inference formats.

YOLOX

1

Anchor-Free Detection

Eliminates anchor boxes from the detection pipeline, removing hyperparameter tuning for anchor dimensions and aspect ratios. Simplifies training workflow while maintaining accuracy comparable to anchor-based YOLO versions.

2

Multi-Framework Deployment

Export trained models to ONNX, TensorRT, ncnn, OpenVINO, and MegEngine with built-in conversion scripts. Enables deployment across cloud GPUs, edge devices, and mobile hardware without manual optimization.

3

Scalable Model Variants

Provides five model sizes from Nano (0.91M parameters) to X (99.1M parameters) with consistent architecture. Allows selection based on target hardware constraints, from resource-limited embedded devices to high-performance server inference.


import torch
from yolox.exp import get_exp

exp = get_exp(None, "yolox-s")
model = exp.get_model()
ckpt = torch.load("yolox_s.pth", map_location="cpu")
model.load_state_dict(ckpt["model"])
model.eval()

img = torch.randn(1, 3, 640, 640)
outputs = model(img)

v0.3.0

YOLOX 0.3.0 adds torch.hub integration, just-in-time compilation, wandb logging support, and various demo and deployment improvements.

  • support loading YOLOX model through torch.hub
  • support just-in-time compile op
  • support wandb logger
  • support freeze function for torch module
  • support showing YOLOX demo in a live window
v0.2.0

This release makes YOLOX installable via pip and includes significant memory optimizations and evaluation improvements.

  • Saved 30% memory useage in COCO training
  • Log per class AP & AP during evaluation
  • Users could install yolox from pip now! Supports on more platform is coming
  • Optimize dynamic matching in label assignment
v0.1.1rc0

This release introduces 2x faster training through optimized preprocessing and image caching, removes Apex dependency in favor of torch amp.

  • Support image caching for faster training, which requires large system RAM
  • Remove the dependence of apex and support torch amp training
  • Optimize the preprocessing for faster training
  • Replace the older distort augmentation with new HSV aug for faster training and better performance

See how people are using YOLOX

Loading tweets...


[ EXPLORE MORE ]

Related Repositories

Discover similar tools and frameworks used by developers