Ultralytics YOLOv5 supports object detection, instance segmentation, classification, training, and export in PyTorch.
Yolov3
This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.

About Yolov3
Yolov3 is a PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for object detection. It predicts bounding boxes and class probabilities directly from full images in one forward pass, and includes tooling for training, validation, inference, and export.
It supports inference through PyTorch Hub and a detect.py script on images, video, webcam, screenshots, directories, and network streams, with results saved to runs/detect. It supports training on COCO and custom data, validation with val.py, and export to TorchScript, ONNX, OpenVINO, TensorRT, CoreML, and PaddlePaddle. Installation requires Python >=3.8.0 with PyTorch >=1.8, and commercial use requires an Enterprise License.
Key features
- Implements YOLOv3, YOLOv3-SPP, and YOLOv3-tiny in PyTorch
- Runs inference on images, video, webcam, screenshots, and streams
- Loads models via PyTorch Hub with automatic weight download
- Trains on COCO or custom datasets with configurable settings
- Validates detection accuracy using val.py script
- Exports to TorchScript, ONNX, OpenVINO, TensorRT, CoreML, PaddlePaddle
- Includes three YOLOv3 variants with training, validation, and inference scripts
- Accepts varied inference sources including webcam and RTSP, RTMP, HTTP streams
- Supports export to multiple deployment formats
- Requires Python 3.8 or later with PyTorch 1.8 or later
- Commercial use requires requesting an Enterprise License
Yolov3 at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Yolov3 alternatives
Tools and sites you could use instead, ranked by how closely they match.
This repository provides semantic segmentation models with more than 500 pretrained convolutional and transformer backbones.
The lightly Python library supports self supervised learning on images.
Detectron2 provides computer vision tools for object detection, segmentation, and other visual recognition tasks.
AwaDB provides an AI-focused embedding vector database with real-time search features.
OpenPose detects body, face, hand, and foot keypoints for multiple people in real time.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Yolov3 FAQ
Which models are included in the repository?
What is required to install it?
Which export formats are supported?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












