description: Learn how to install the Ultralytics package in developer mode and build/serve locally using MkDocs. Deploy your project to your host easily.
---
# Ultralytics Docs
Ultralytics Docs are deployed to [https://docs.ultralytics.com](https://docs.ultralytics.com).
@ -82,4 +86,4 @@ for your repository and updating the "Custom domain" field in the "GitHub Pages"
description: Learn how torchvision organizes classification image datasets. Use this code to create and train models. CLI and Python code shown.
---
# Image Classification Datasets Overview
@ -77,6 +78,7 @@ cifar-10-/
In this example, the `train` directory contains subdirectories for each class in the dataset, and each class subdirectory contains all the images for that class. The `test` directory has a similar structure. The `root` directory also contains other files that are part of the CIFAR10 dataset.
## Usage
!!! example ""
=== "Python"
@ -98,4 +100,5 @@ In this example, the `train` directory contains subdirectories for each class in
description: Learn about the COCO dataset, designed to encourage research on object detection, segmentation, and captioning with standardized evaluation metrics.
description: Learn about supported dataset formats for training YOLO detection models, including Ultralytics YOLO and COCO, in this Object Detection Datasets Overview.
---
# Object Detection Datasets Overview
@ -15,11 +16,12 @@ The dataset format used for training YOLO detection models is as follows:
1. One text file per image: Each image in the dataset has a corresponding text file with the same name as the image file and the ".txt" extension.
2. One row per object: Each row in the text file corresponds to one object instance in the image.
3. Object information per row: Each row contains the following information about the object instance:
- Object class index: An integer representing the class of the object (e.g., 0 for person, 1 for car, etc.).
- Object center coordinates: The x and y coordinates of the center of the object, normalized to be between 0 and 1.
- Object width and height: The width and height of the object, normalized to be between 0 and 1.
- Object class index: An integer representing the class of the object (e.g., 0 for person, 1 for car, etc.).
- Object center coordinates: The x and y coordinates of the center of the object, normalized to be between 0 and 1.
- Object width and height: The width and height of the object, normalized to be between 0 and 1.
The format for a single row in the detection dataset file is as follows:
```
<object-class><x><y><width><height>
```
@ -55,6 +57,7 @@ The `names` field is a list of the names of the object classes. The order of the
NOTE: Either `nc` or `names` must be defined. Defining both are not mandatory
Alternatively, you can directly define class names like this:
```yaml
names:
0: person
@ -72,6 +75,7 @@ names: ['person', 'car']
```
## Usage
!!! example ""
=== "Python"
@ -93,6 +97,7 @@ names: ['person', 'car']
```
## Supported Datasets
TODO
## Port or Convert label formats
@ -103,4 +108,4 @@ TODO
from ultralytics.yolo.data.converter import convert_coco
description: Ultralytics provides support for various datasets to facilitate multiple computer vision tasks. Check out our list of main datasets and their summaries.
---
# Datasets Overview
@ -10,48 +11,48 @@ Ultralytics provides support for various datasets to facilitate computer vision
Bounding box object detection is a computer vision technique that involves detecting and localizing objects in an image by drawing a bounding box around each object.
* [Argoverse](detect/argoverse.md): A dataset containing 3D tracking and motion forecasting data from urban environments with rich annotations.
* [COCO](detect/coco.md): A large-scale dataset designed for object detection, segmentation, and captioning with over 200K labeled images.
* [COCO8](detect/coco8.md): Contains the first 4 images from COCO train and COCO val, suitable for quick tests.
* [Global Wheat 2020](detect/globalwheat2020.md): A dataset of wheat head images collected from around the world for object detection and localization tasks.
* [Objects365](detect/objects365.md): A high-quality, large-scale dataset for object detection with 365 object categories and over 600K annotated images.
* [SKU-110K](detect/sku-110k.md): A dataset featuring dense object detection in retail environments with over 11K images and 1.7 million bounding boxes.
* [VisDrone](detect/visdrone.md): A dataset containing object detection and multi-object tracking data from drone-captured imagery with over 10K images and video sequences.
* [VOC](detect/voc.md): The Pascal Visual Object Classes (VOC) dataset for object detection and segmentation with 20 object classes and over 11K images.
* [xView](detect/xview.md): A dataset for object detection in overhead imagery with 60 object categories and over 1 million annotated objects.
* [Argoverse](detect/argoverse.md): A dataset containing 3D tracking and motion forecasting data from urban environments with rich annotations.
* [COCO](detect/coco.md): A large-scale dataset designed for object detection, segmentation, and captioning with over 200K labeled images.
* [COCO8](detect/coco8.md): Contains the first 4 images from COCO train and COCO val, suitable for quick tests.
* [Global Wheat 2020](detect/globalwheat2020.md): A dataset of wheat head images collected from around the world for object detection and localization tasks.
* [Objects365](detect/objects365.md): A high-quality, large-scale dataset for object detection with 365 object categories and over 600K annotated images.
* [SKU-110K](detect/sku-110k.md): A dataset featuring dense object detection in retail environments with over 11K images and 1.7 million bounding boxes.
* [VisDrone](detect/visdrone.md): A dataset containing object detection and multi-object tracking data from drone-captured imagery with over 10K images and video sequences.
* [VOC](detect/voc.md): The Pascal Visual Object Classes (VOC) dataset for object detection and segmentation with 20 object classes and over 11K images.
* [xView](detect/xview.md): A dataset for object detection in overhead imagery with 60 object categories and over 1 million annotated objects.
Instance segmentation is a computer vision technique that involves identifying and localizing objects in an image at the pixel level.
* [COCO](segment/coco.md): A large-scale dataset designed for object detection, segmentation, and captioning tasks with over 200K labeled images.
* [COCO8-seg](segment/coco8-seg.md): A smaller dataset for instance segmentation tasks, containing a subset of 8 COCO images with segmentation annotations.
* [COCO](segment/coco.md): A large-scale dataset designed for object detection, segmentation, and captioning tasks with over 200K labeled images.
* [COCO8-seg](segment/coco8-seg.md): A smaller dataset for instance segmentation tasks, containing a subset of 8 COCO images with segmentation annotations.
## [Pose Estimation](pose/index.md)
Pose estimation is a technique used to determine the pose of the object relative to the camera or the world coordinate system.
* [COCO](pose/coco.md): A large-scale dataset with human pose annotations designed for pose estimation tasks.
* [COCO8-pose](pose/coco8-pose.md): A smaller dataset for pose estimation tasks, containing a subset of 8 COCO images with human pose annotations.
* [COCO](pose/coco.md): A large-scale dataset with human pose annotations designed for pose estimation tasks.
* [COCO8-pose](pose/coco8-pose.md): A smaller dataset for pose estimation tasks, containing a subset of 8 COCO images with human pose annotations.
## [Classification](classify/index.md)
Image classification is a computer vision task that involves categorizing an image into one or more predefined classes or categories based on its visual content.
* [Caltech 101](classify/caltech101.md): A dataset containing images of 101 object categories for image classification tasks.
* [Caltech 256](classify/caltech256.md): An extended version of Caltech 101 with 256 object categories and more challenging images.
* [CIFAR-10](classify/cifar10.md): A dataset of 60K 32x32 color images in 10 classes, with 6K images per class.
* [CIFAR-100](classify/cifar100.md): An extended version of CIFAR-10 with 100 object categories and 600 images per class.
* [Fashion-MNIST](classify/fashion-mnist.md): A dataset consisting of 70,000 grayscale images of 10 fashion categories for image classification tasks.
* [ImageNet](classify/imagenet.md): A large-scale dataset for object detection and image classification with over 14 million images and 20,000 categories.
* [ImageNet-10](classify/imagenet10.md): A smaller subset of ImageNet with 10 categories for faster experimentation and testing.
* [Imagenette](classify/imagenette.md): A smaller subset of ImageNet that contains 10 easily distinguishable classes for quicker training and testing.
* [Imagewoof](classify/imagewoof.md): A more challenging subset of ImageNet containing 10 dog breed categories for image classification tasks.
* [MNIST](classify/mnist.md): A dataset of 70,000 grayscale images of handwritten digits for image classification tasks.
* [Caltech 101](classify/caltech101.md): A dataset containing images of 101 object categories for image classification tasks.
* [Caltech 256](classify/caltech256.md): An extended version of Caltech 101 with 256 object categories and more challenging images.
* [CIFAR-10](classify/cifar10.md): A dataset of 60K 32x32 color images in 10 classes, with 6K images per class.
* [CIFAR-100](classify/cifar100.md): An extended version of CIFAR-10 with 100 object categories and 600 images per class.
* [Fashion-MNIST](classify/fashion-mnist.md): A dataset consisting of 70,000 grayscale images of 10 fashion categories for image classification tasks.
* [ImageNet](classify/imagenet.md): A large-scale dataset for object detection and image classification with over 14 million images and 20,000 categories.
* [ImageNet-10](classify/imagenet10.md): A smaller subset of ImageNet with 10 categories for faster experimentation and testing.
* [Imagenette](classify/imagenette.md): A smaller subset of ImageNet that contains 10 easily distinguishable classes for quicker training and testing.
* [Imagewoof](classify/imagewoof.md): A more challenging subset of ImageNet containing 10 dog breed categories for image classification tasks.
* [MNIST](classify/mnist.md): A dataset of 70,000 grayscale images of handwritten digits for image classification tasks.
## [Multi-Object Tracking](track/index.md)
Multi-object tracking is a computer vision technique that involves detecting and tracking multiple objects over time in a video sequence.
* [Argoverse](detect/argoverse.md): A dataset containing 3D tracking and motion forecasting data from urban environments with rich annotations for multi-object tracking tasks.
* [VisDrone](detect/visdrone.md): A dataset containing object detection and multi-object tracking data from drone-captured imagery with over 10K images and video sequences.
* [VisDrone](detect/visdrone.md): A dataset containing object detection and multi-object tracking data from drone-captured imagery with over 10K images and video sequences.
In this format, `<class-index>` is the index of the class for the object,`<x><y><width><height>` are coordinates of boudning box, and `<px1> <py1> <px2> <py2> <pxn> <pyn>` are the pixel coordinates of the keypoints. The coordinates are separated by spaces.
In this format, `<class-index>` is the index of the class for the object,`<x><y><width><height>` are coordinates of boudning box, and `<px1> <py1> <px2> <py2> ... <pxn> <pyn>` are the pixel coordinates of the keypoints. The coordinates are separated by spaces.
** Dataset file format **
@ -62,6 +63,7 @@ The `names` field is a list of the names of the object classes. The order of the
NOTE: Either `nc` or `names` must be defined. Defining both are not mandatory
Alternatively, you can directly define class names like this:
```
names:
0: person
@ -69,7 +71,7 @@ names:
```
(Optional) if the points are symmetric then need flip_idx, like left-right side of human or face.
For example let's say there're five keypoints of facial landmark: [left eye, right eye, nose, left point of mouth, right point of mouse], and the original index is [0, 1, 2, 3, 4], then flip_idx is [1, 0, 2, 4, 3].(just exchange the left-right index, i.e 0-1 and 3-4, and do not modify others like nose in this example)
For example let's say there're five keypoints of facial landmark: [left eye, right eye, nose, left point of mouth, right point of mouse], and the original index is [0, 1, 2, 3, 4], then flip_idx is [1, 0, 2, 4, 3].(just exchange the left-right index, i.e 0-1 and 3-4, and do not modify others like nose in this example)
description: Learn about the Ultralytics YOLO dataset format for segmentation models. Use YAML to train Detection Models. Convert COCO to YOLO format using Python.
---
# Instance Segmentation Datasets Overview
@ -15,8 +16,8 @@ The dataset format used for training YOLO segmentation models is as follows:
1. One text file per image: Each image in the dataset has a corresponding text file with the same name as the image file and the ".txt" extension.
2. One row per object: Each row in the text file corresponds to one object instance in the image.
3. Object information per row: Each row contains the following information about the object instance:
- Object class index: An integer representing the class of the object (e.g., 0 for person, 1 for car, etc.).
- Object bounding coordinates: The bounding coordinates around the mask area, normalized to be between 0 and 1.
- Object class index: An integer representing the class of the object (e.g., 0 for person, 1 for car, etc.).
- Object bounding coordinates: The bounding coordinates around the mask area, normalized to be between 0 and 1.
The format for a single row in the segmentation dataset file is as follows:
@ -24,7 +25,7 @@ The format for a single row in the segmentation dataset file is as follows:
<class-index><x1><y1><x2><y2> ... <xn><yn>
```
In this format, `<class-index>` is the index of the class for the object, and `<x1> <y1> <x2> <y2> ... <xn> <yn>` are the bounding coordinates of the object's segmentation mask. The coordinates are separated by spaces.
In this format, `<class-index>` is the index of the class for the object, and `<x1> <y1> <x2> <y2> ... <xn> <yn>` are the bounding coordinates of the object's segmentation mask. The coordinates are separated by spaces.
Here is an example of the YOLO dataset format for a single image with two object instances:
@ -32,6 +33,7 @@ Here is an example of the YOLO dataset format for a single image with two object
description: Discover the datasets compatible with Multi-Object Detector. Train your trackers and make your detections more efficient with Ultralytics' YOLO.
---
# Multi-object Tracking Datasets Overview
@ -25,5 +26,4 @@ Support for training trackers alone is coming soon
```bash
yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" conf=0.3, iou=0.5 show
description: Individual Contributor License Agreement. Settle Intellectual Property issues for Contributions made to anything open source released by Ultralytics.
description: Read the Ultralytics Contributor Covenant Code of Conduct. Learn ways to create a welcoming community & consequences for inappropriate conduct.
---
# Ultralytics Contributor Covenant Code of Conduct
@ -110,7 +111,7 @@ Violating these terms may lead to a permanent ban.
### 4. Permanent Ban
**Community Impact**: Demonstrating a pattern of violation of community
standards, including sustained inappropriate behavior, harassment of an
standards, including sustained inappropriate behavior, harassment of an
individual, or aggression toward or disparagement of classes of individuals.
**Consequence**: A permanent ban from any sort of public interaction within
@ -129,4 +130,4 @@ For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at
description: Learn how to contribute to Ultralytics Open-Source YOLO Repositories with contributions guidelines, pull requests requirements, and GitHub CI tests.
---
# Contributing to Ultralytics Open-Source YOLO Repositories
@ -10,11 +11,11 @@ First of all, thank you for your interest in contributing to Ultralytics open-so
description: Get comprehensive resources for Ultralytics YOLO repositories. Find guides, FAQs, MRE creation, CLA & more. Join the supportive community now!
---
Welcome to the Ultralytics Help page! We are committed to providing you with comprehensive resources to make your experience with Ultralytics YOLO repositories as smooth and enjoyable as possible. On this page, you'll find essential links to guides and documents that will help you navigate through common tasks and address any questions you might have while using our repositories.
description: Learn how to create a Minimum Reproducible Example (MRE) for Ultralytics YOLO bug reports to help maintainers and contributors understand your issue better.
---
# Creating a Minimum Reproducible Example for Bug Reports in Ultralytics YOLO Repositories
description: Run YOLO models on your Android device for real-time object detection with Ultralytics Android App. Utilizes TensorFlow Lite and hardware delegates.
---
# Ultralytics Android App: Real-time Object Detection with YOLO Models
INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in mean average precision (mAP) due to the lower numerical precision.
!!! tip "mAP Reduction in INT8 Models"
The reduced numerical precision in INT8 models can lead to some loss of information during the quantization process, which may result in a slight decrease in mAP. However, this trade-off is often acceptable considering the substantial performance gains offered by INT8 quantization.
## Delegates and Performance Variability
@ -61,4 +62,4 @@ To get started with the Ultralytics Android App, follow these steps:
6. Explore the app's settings to adjust the detection threshold, enable or disable specific object classes, and more.
With the Ultralytics Android App, you now have the power of real-time object detection using YOLO models right at your fingertips. Enjoy exploring the app's features and optimizing its settings to suit your specific use cases.
With the Ultralytics Android App, you now have the power of real-time object detection using YOLO models right at your fingertips. Enjoy exploring the app's features and optimizing its settings to suit your specific use cases.
description: Get started with the Ultralytics iOS app and run YOLO models in real-time for object detection on your iPhone or iPad with the Apple Neural Engine.
---
# Ultralytics iOS App: Real-time Object Detection with YOLO Models
@ -33,7 +34,6 @@ By combining quantized YOLO models with the Apple Neural Engine, the Ultralytics
Please note that this list only includes iPhone models from 2017 onwards, and the ANE TOPs values are approximate.
## Getting Started with the Ultralytics iOS App
@ -52,4 +52,4 @@ To get started with the Ultralytics iOS App, follow these steps:
6. Explore the app's settings to adjust the detection threshold, enable or disable specific object classes, and more.
With the Ultralytics iOS App, you can now leverage the power of YOLO models for real-time object detection on your iPhone or iPad, powered by the Apple Neural Engine and optimized with FP16 or INT8 quantization.
With the Ultralytics iOS App, you can now leverage the power of YOLO models for real-time object detection on your iPhone or iPad, powered by the Apple Neural Engine and optimized with FP16 or INT8 quantization.
description: 'Ultralytics HUB: Train & deploy YOLO models from one spot! Use drag-and-drop interface with templates & pre-training models. Check quickstart, datasets, and more.'
---
# Ultralytics HUB
@ -20,7 +21,6 @@ comments: true
launch [Ultralytics HUB](https://bit.ly/ultralytics_hub), a new web tool for training and deploying all your YOLOv5 and YOLOv8 🚀
models from one spot!
## Introduction
HUB is designed to be user-friendly and intuitive, with a drag-and-drop interface that allows users to
This page is currently under construction!️ 👷Please check back later for updates. 😃🔜
# YOLO Inference API
The YOLO Inference API allows you to access the YOLOv8 object detection capabilities via a RESTful API. This enables you to run object detection on images without the need to install and set up the YOLOv8 environment locally.
@ -45,7 +44,6 @@ print(response.json())
In this example, replace `API_KEY` with your actual API key, `MODEL_ID` with the desired model ID, and `path/to/image.jpg` with the path to the image you want to analyze.
## Example Usage with CLI
You can use the YOLO Inference API with the command-line interface (CLI) by utilizing the `curl` command. Replace `API_KEY` with your actual API key, `MODEL_ID` with the desired model ID, and `image.jpg` with the path to the image you want to analyze:
@ -334,7 +332,6 @@ YOLO segmentation models, such as `yolov8n-seg.pt`, can return JSON responses fr
}
```
### Pose Model Format
YOLO pose models, such as `yolov8n-pose.pt`, can return JSON responses from local inference, CLI API inference, and Python API inference. All of these methods produce the same JSON response format.
description: Explore Ultralytics YOLOv8, a cutting-edge real-time object detection and image segmentation model for various applications and hardware platforms.
---
<divalign="center">
@ -23,7 +24,7 @@ Explore the YOLOv8 Docs, a comprehensive resource designed to help you understan
## Where to Start
- **Install**`ultralytics` with pip and get up and running in minutes [:material-clock-fast: Get Started](quickstart.md){ .md-button }
- **Predict** new images and videos with YOLOv8 [:octicons-image-16: Predict on Images](modes/predict.md){ .md-button }
- **Predict** new images and videos with YOLOv8 [:octicons-image-16: Predict on Images](modes/predict.md){ .md-button }
- **Train** a new YOLOv8 model on your own custom dataset [:fontawesome-solid-brain: Train a Model](modes/train.md){ .md-button }
- **Explore** YOLOv8 tasks like segment, classify, pose and track [:material-magnify-expand: Explore Tasks](tasks/index.md){ .md-button }
@ -37,4 +38,4 @@ Explore the YOLOv8 Docs, a comprehensive resource designed to help you understan
- [YOLOv5](https://github.com/ultralytics/yolov5) further improved the model's performance and added new features such as hyperparameter optimization, integrated experiment tracking and automatic export to popular export formats.
- [YOLOv6](https://github.com/meituan/YOLOv6) was open-sourced by [Meituan](https://about.meituan.com/) in 2022 and is in use in many of the company's autonomous delivery robots.
- [YOLOv7](https://github.com/WongKinYiu/yolov7) added additional tasks such as pose estimation on the COCO keypoints dataset.
- [YOLOv8](https://github.com/ultralytics/ultralytics) is the latest version of YOLO by Ultralytics. As a cutting-edge, state-of-the-art (SOTA) model, YOLOv8 builds on the success of previous versions, introducing new features and improvements for enhanced performance, flexibility, and efficiency. YOLOv8 supports a full range of vision AI tasks, including [detection](tasks/detect.md), [segmentation](tasks/segment.md), [pose estimation](tasks/pose.md), [tracking](modes/track.md), and [classification](tasks/classify.md). This versatility allows users to leverage YOLOv8's capabilities across diverse applications and domains.
- [YOLOv8](https://github.com/ultralytics/ultralytics) is the latest version of YOLO by Ultralytics. As a cutting-edge, state-of-the-art (SOTA) model, YOLOv8 builds on the success of previous versions, introducing new features and improvements for enhanced performance, flexibility, and efficiency. YOLOv8 supports a full range of vision AI tasks, including [detection](tasks/detect.md), [segmentation](tasks/segment.md), [pose estimation](tasks/pose.md), [tracking](modes/track.md), and [classification](tasks/classify.md). This versatility allows users to leverage YOLOv8's capabilities across diverse applications and domains.
description: Learn about the supported models and architectures, such as YOLOv3, YOLOv5, and YOLOv8, and how to contribute your own model to Ultralytics.
description: Detect objects faster and more accurately using Ultralytics YOLOv5u. Find pre-trained models for each task, including Inference, Validation and Training.
description: Benchmark mode compares speed and accuracy of various YOLOv8 export formats like ONNX or OpenVINO. Optimize formats for speed or accuracy.
description: 'Export mode: Create a deployment-ready YOLOv8 model by converting it to various formats. Export to ONNX or OpenVINO for up to 3x CPU speedup.'
| `conf (bool)` | Whether to plot the detection confidence score. |
@ -234,7 +237,6 @@ masks, classification logits, etc.) found in the results object
| `masks (bool)` | Whether to plot the masks. |
| `probs (bool)` | Whether to plot classification probability. |
## Streaming Source `for`-loop
Here's a Python script using OpenCV (cv2) and YOLOv8 to run inference on video frames. This script assumes you have already installed the necessary packages (opencv-python and ultralytics).
@ -277,4 +279,4 @@ Here's a Python script using OpenCV (cv2) and YOLOv8 to run inference on video f
# Release the video capture object and close the display window
description: Install and use YOLOv8 via CLI or Python. Run single-line commands or integrate with Python projects for object detection, segmentation, and classification.
---
## Install
@ -32,13 +33,11 @@ See the `ultralytics` [requirements.txt](https://github.com/ultralytics/ultralyt
The YOLO command line interface (CLI) allows for simple single-line commands without the need for a Python environment.
CLI requires no customization or Python code. You can simply run all tasks from the terminal with the `yolo` command. Check out the [CLI Guide](usage/cli.md) to learn more about using YOLOv8 from the command line.
!!! example
=== "Syntax"
@ -93,7 +92,6 @@ CLI requires no customization or Python code. You can simply run all tasks from
yolo cfg
```
!!! warning "Warning"
Arguments must be passed as `arg=val` pairs, split by an equals `=` sign and delimited by spaces ` ` between pairs. Do not use `--` argument prefixes or commas `,` between arguments.
@ -134,4 +132,4 @@ For example, users can load a model, train it, evaluate its performance on a val
description: Explore Ultralytics events, including 'request_with_credentials' and 'smart_request', to improve your project's performance and efficiency.
description: Detect 80+ object categories with bounding box coordinates and class probabilities using AutoShape in Ultralytics YOLO. Explore Detections now.
description: Learn how to register custom event-tracking and track predictions with Ultralytics YOLO via on_predict_start and register_tracker methods.
description: 'TrackState: A comprehensive guide to Ultralytics tracker''s BaseTrack for monitoring model performance. Improve your tracking capabilities now!'
description: '"Optimize tracking with Ultralytics BOTrack. Easily sort and track bots with BOTSORT. Streamline data collection for improved performance."'
description: '"Track Google Marketing Campaigns in GMC with Ultralytics Tracker. Learn to set up and use GMC for detailed analytics. Get started now."'
description: Learn how to match and fuse object detections for accurate target tracking using Ultralytics' YOLO merge_matches, iou_distance, and embedding_distance.
description: Learn how to use auto_annotate in Ultralytics YOLO to generate annotations automatically for your dataset. Simplify object detection workflows.
description: Learn about BaseDataset in Ultralytics YOLO, a flexible dataset class for object detection. Maximize your YOLO performance with custom datasets.
description: Convert COCO-91 to COCO-80 class, RLE to polygon, and merge multi-segment images with Ultralytics YOLO data converter. Improve your object detection.
description: 'Ultralytics YOLO Docs: Learn about stream loaders for image and tensor data, as well as autocasting techniques. Check out SourceTypes and more.'
description: Create custom YOLOv5 datasets with Ultralytics YOLODataset and SemanticDataset. Streamline your object detection and segmentation projects.
description: Learn about BaseTensor & Boxes in Ultralytics YOLO Engine. Check out Ultralytics Docs for quality tutorials and resources on object detection.
description: Dynamically adjusts input size to optimize GPU memory usage during training. Learn how to use check_train_batch_size with Ultralytics YOLO.
description: Improve your YOLOv5 model training with callbacks from ClearML. Learn about log debug samples, pre-training routines, validation and more.
description: Learn about YOLO callbacks using the Comet.ml platform, enhancing object detection training and testing with custom logging and visualizations.
description: Improve YOLOv5 model training with Ultralytics' on-train callbacks. Boost performance on-pretrain-routine-end, model-save, train/predict start.
description: '"Improve YOLO model performance with on_fit_epoch_end callback. Learn to integrate with Ray Tune for hyperparameter tuning. Ultralytics YOLO docs."'
description: Learn how to use Ultralytics YOLO's built-in callbacks `on_pretrain_routine_start` and `on_train_epoch_end` for improved training performance.
description: Learn about Bounding Boxes (Bboxes) and _ntuple in Ultralytics YOLO for object detection. Improve accuracy and speed with these powerful tools.
description: 'Discover the power of YOLO''s plotting functions: Colors, Labels and Images. Code examples to output targets and visualize features. Check it now.'
description: Improve your YOLO models with Ultralytics' TaskAlignedAssigner, select_highest_overlaps, and dist2bbox utilities. Streamline your workflow today.
description: Boost posture detection using PoseTrainer and train models using train() API. Learn PoseLoss for ultra-fast and accurate pose detection with Ultralytics YOLO.
description: '"Use SegmentationPredictor in YOLOv8 for efficient object detection and segmentation. Explore Ultralytics YOLO Docs for more information."'
description: Learn about SegmentationTrainer and Train in Ultralytics YOLO v8 for efficient object detection models. Improve your training with Ultralytics Docs.
Glenn Jocher
2 years ago
committed by
GitHub