🕷️ Crawler Inspector

URL Lookup

Direct Parameter Lookup

Raw Queries and Responses

1. Shard Calculation

Query:
Response:
Calculated Shard: 133 (from laksa033)

2. Crawled Status Check

Query:
Response:

3. Robots.txt Check

Query:
Response:

4. Spam/Ban Check

Query:
Response:

5. Seen Status Check

ℹ️ Skipped - page is already crawled

📄
INDEXABLE
✅
CRAWLED
10 days ago
🤖
ROBOTS ALLOWED

Page Info Filters

FilterStatusConditionDetails
HTTP statusPASSdownload_http_code = 200HTTP 200
Age cutoffPASSdownload_stamp > now() - 6 MONTH0.3 months ago
History dropPASSisNull(history_drop_reason)No drop reason
Spam/banPASSfh_dont_index != 1 AND ml_spam_score = 0ml_spam_score=0
CanonicalPASSmeta_canonical IS NULL OR = '' OR = src_unparsedNot set

Page Details

PropertyValue
URLhttps://docs.ultralytics.com/quickstart/
Last Crawled2026-04-05 08:24:39 (10 days ago)
First Indexed2023-01-11 07:08:30 (3 years ago)
HTTP Status Code200
Meta TitleInstall Ultralytics - Ultralytics YOLO Docs
Meta DescriptionLearn how to install Ultralytics using pip, conda, or Docker. Follow our step-by-step guide for a seamless setup of Ultralytics YOLO.
Meta Canonicalnull
Boilerpipe Text
Ultralytics offers a variety of installation methods, including pip, conda, and Docker. You can install YOLO via the ultralytics pip package for the latest stable release, or by cloning the Ultralytics GitHub repository for the most current version. Docker is also an option to run the package in an isolated container, which avoids local installation. Watch: Ultralytics YOLO Quick Start Guide Install Install or update the ultralytics package using pip by running pip install -U ultralytics . For more details on the ultralytics package, visit the Python Package Index (PyPI) . # Install or upgrade the ultralytics package from PyPI pip install -U ultralytics You can also install ultralytics directly from the Ultralytics GitHub repository . This can be useful if you want the latest development version. Ensure you have the Git command-line tool installed, and then run: # Install the ultralytics package from GitHub pip install git+https://github.com/ultralytics/ultralytics.git@main Conda can be used as an alternative package manager to pip. For more details, visit Anaconda . The Ultralytics feedstock repository for updating the conda package is available at GitHub . # Install the ultralytics package using conda conda install -c conda-forge ultralytics Note If you are installing in a CUDA environment, it is best practice to install ultralytics , pytorch , and pytorch-cuda in the same command. This allows the conda package manager to resolve any conflicts. Alternatively, install pytorch-cuda last to override the CPU-specific pytorch package if necessary. # Install all packages together using conda conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda = 11 .8 ultralytics Conda Docker Image Ultralytics Conda Docker images are also available on Docker Hub . These images are based on Miniconda3 and provide a straightforward way to start using ultralytics in a Conda environment. # Set image name as a variable t = ultralytics/ultralytics:latest-conda # Pull the latest ultralytics image from Docker Hub sudo docker pull $t # Run the ultralytics image in a container with GPU support sudo docker run -it --ipc = host --runtime = nvidia --gpus all $t # all GPUs sudo docker run -it --ipc = host --runtime = nvidia --gpus '"device=2,3"' $t # specify GPUs Clone the Ultralytics GitHub repository if you are interested in contributing to development or wish to experiment with the latest source code. After cloning, navigate into the directory and install the package in editable mode -e using pip. # Clone the ultralytics repository git clone https://github.com/ultralytics/ultralytics # Navigate to the cloned directory cd ultralytics # Install the package in editable mode for development pip install -e . Use Docker to execute the ultralytics package in an isolated container, ensuring consistent performance across various environments. By selecting one of the official ultralytics images from Docker Hub , you avoid the complexity of local installation and gain access to a verified working environment. Ultralytics offers five main supported Docker images, each designed for high compatibility and efficiency: Dockerfile: GPU image recommended for training. Dockerfile-arm64: Optimized for ARM64 architecture, suitable for deployment on devices like Raspberry Pi and other ARM64-based platforms. Dockerfile-cpu: Ubuntu-based CPU-only version, suitable for inference and environments without GPUs. Dockerfile-jetson: Tailored for NVIDIA Jetson devices, integrating GPU support optimized for these platforms. Dockerfile-python: Minimal image with just Python and necessary dependencies, ideal for lightweight applications and development. Dockerfile-conda: Based on Miniconda3 with a conda installation of the ultralytics package. Here are the commands to get the latest image and execute it: # Set image name as a variable t = ultralytics/ultralytics:latest # Pull the latest ultralytics image from Docker Hub sudo docker pull $t # Run the ultralytics image in a container with GPU support sudo docker run -it --ipc = host --runtime = nvidia --gpus all $t # all GPUs sudo docker run -it --ipc = host --runtime = nvidia --gpus '"device=2,3"' $t # specify GPUs The above command initializes a Docker container with the latest ultralytics image. The -it flags assign a pseudo-TTY and keep stdin open, allowing interaction with the container. The --ipc=host flag sets the IPC (Inter-Process Communication) namespace to the host, which is essential for sharing memory between processes. The --gpus all flag enables access to all available GPUs inside the container, crucial for tasks requiring GPU computation. Note: To work with files on your local machine within the container, use Docker volumes to mount a local directory into the container: # Mount local directory to a directory inside the container sudo docker run -it --ipc = host --runtime = nvidia --gpus all -v /path/on/host:/path/in/container $t Replace /path/on/host with the directory path on your local machine, and /path/in/container with the desired path inside the Docker container. For advanced Docker usage, explore the Ultralytics Docker Guide . See the ultralytics pyproject.toml file for a list of dependencies. Note that all examples above install all required dependencies. Tip PyTorch requirements vary by operating system and CUDA requirements, so install PyTorch first by following the instructions at PyTorch . Headless Server Installation For server environments without a display (e.g., cloud VMs, Docker containers, CI/CD pipelines), use the ultralytics-opencv-headless package. This is identical to the standard ultralytics package but depends on opencv-python-headless instead of opencv-python , avoiding unnecessary GUI dependencies and potential libGL errors. Headless Install pip install ultralytics-opencv-headless Both packages provide the same functionality and API. The headless variant simply excludes OpenCV's GUI components that require display libraries. Advanced Installation While the standard installation methods cover most use cases, you might need a more tailored setup for development or custom configurations. Advanced Methods If you need persistent custom modifications, you can fork the Ultralytics repository, make changes to pyproject.toml or other code, and install from your fork. Fork the Ultralytics GitHub repository to your own GitHub account. Clone your fork locally: git clone https://github.com/YOUR_USERNAME/ultralytics.git cd ultralytics Create a new branch for your changes: git checkout -b my-custom-branch Make your modifications to pyproject.toml or other files as needed. Commit and push your changes: git add . git commit -m "My custom changes" git push origin my-custom-branch Install using pip with the git+https syntax, pointing to your branch: pip install git+https://github.com/YOUR_USERNAME/ultralytics.git@my-custom-branch Clone the repository locally, modify files as needed, and install in editable mode. Clone the Ultralytics repository: git clone https://github.com/ultralytics/ultralytics cd ultralytics Make your modifications to pyproject.toml or other files as needed. Install the package in editable mode ( -e ). Pip will use your modified pyproject.toml to resolve dependencies: pip install -e . This approach is useful for development or testing local changes before committing. Specify a custom Ultralytics fork in your requirements.txt file to ensure consistent installations across your team. requirements.txt # Install ultralytics from a specific git branch git+https://github.com/YOUR_USERNAME/ultralytics.git@my-custom-branch # Other project dependencies flask Install dependencies from the file: pip install -r requirements.txt Use Ultralytics with CLI The Ultralytics command-line interface (CLI) allows for simple single-line commands without needing a Python environment. CLI requires no customization or Python code; run all tasks from the terminal with the yolo command. For more on using YOLO from the command line, see the CLI Guide . Example Train a detection model for 10 epochs with an initial learning rate of 0.01: yolo train data = coco8.yaml model = yolo26n.pt epochs = 10 lr0 = 0 .01 Predict a YouTube video using a pretrained segmentation model at image size 320: yolo predict model = yolo26n-seg.pt source = 'https://youtu.be/LNwODJXcvt4' imgsz = 320 Validate a pretrained detection model with a batch size of 1 and image size of 640: yolo val model = yolo26n.pt data = coco8.yaml batch = 1 imgsz = 640 Export a YOLO26n classification model to ONNX format with an image size of 224x128 (no TASK required): yolo export model = yolo26n-cls.pt format = onnx imgsz = 224 ,128 Count objects in a video or live stream using YOLO26: yolo solutions count show = True yolo solutions count source = "path/to/video.mp4" # specify video file path Monitor workout exercises using a YOLO26 pose model: yolo solutions workout show = True yolo solutions workout source = "path/to/video.mp4" # specify video file path # Use keypoints for ab-workouts yolo solutions workout kpts = "[5, 11, 13]" # left side yolo solutions workout kpts = "[6, 12, 14]" # right side Use YOLO26 to count objects in a designated queue or region: yolo solutions queue show = True yolo solutions queue source = "path/to/video.mp4" # specify video file path yolo solutions queue region = "[(20, 400), (1080, 400), (1080, 360), (20, 360)]" # configure queue coordinates Perform object detection, instance segmentation, or pose estimation in a web browser using Streamlit : yolo solutions inference yolo solutions inference model = "path/to/model.pt" # use model fine-tuned with Ultralytics Python package Run special commands to see the version, view settings, run checks, and more: yolo help yolo checks yolo version yolo settings yolo copy-cfg yolo cfg yolo solutions help Warning Arguments must be passed as arg=value pairs, split by an equals = sign and delimited by spaces. Do not use -- argument prefixes or commas , between arguments. yolo predict model=yolo26n.pt imgsz=640 conf=0.25 ✅ yolo predict model yolo26n.pt imgsz 640 conf 0.25 ❌ (missing = ) yolo predict model=yolo26n.pt, imgsz=640, conf=0.25 ❌ (do not use , ) yolo predict --model yolo26n.pt --imgsz 640 --conf 0.25 ❌ (do not use -- ) yolo solution model=yolo26n.pt imgsz=640 conf=0.25 ❌ (use solutions , not solution ) CLI Guide Use Ultralytics with Python The Ultralytics YOLO Python interface offers seamless integration into Python projects, making it easy to load, run, and process model outputs. Designed for simplicity, the Python interface allows users to quickly implement object detection , segmentation, and classification. This makes the YOLO Python interface an invaluable tool for incorporating these functionalities into Python projects. For instance, users can load a model, train it, evaluate its performance, and export it to ONNX format with just a few lines of code. Explore the Python Guide to learn more about using YOLO within your Python projects. Example from ultralytics import YOLO # Create a new YOLO model from scratch model = YOLO ( "yolo26n.yaml" ) # Load a pretrained YOLO model (recommended for training) model = YOLO ( "yolo26n.pt" ) # Train the model using the 'coco8.yaml' dataset for 3 epochs results = model . train ( data = "coco8.yaml" , epochs = 3 ) # Evaluate the model's performance on the validation set results = model . val () # Perform object detection on an image using the model results = model ( "https://ultralytics.com/images/bus.jpg" ) # Export the model to ONNX format success = model . export ( format = "onnx" ) Python Guide Ultralytics Settings The Ultralytics library includes a SettingsManager for fine-grained control over experiments, allowing users to access and modify settings easily. Stored in a JSON file within the environment's user configuration directory, these settings can be viewed or modified in the Python environment or via the Command-Line Interface (CLI). Inspecting Settings To view the current configuration of your settings: View settings Use Python to view your settings by importing the settings object from the ultralytics module. Print and return settings with these commands: from ultralytics import settings # View all settings print ( settings ) # Return a specific setting value = settings [ "runs_dir" ] The command-line interface allows you to check your settings with: yolo settings Modifying Settings Ultralytics makes it easy to modify settings in the following ways: Update settings In Python, use the update method on the settings object: from ultralytics import settings # Update a setting settings . update ({ "runs_dir" : "/path/to/runs" }) # Update multiple settings settings . update ({ "runs_dir" : "/path/to/runs" , "tensorboard" : False }) # Reset settings to default values settings . reset () To modify settings using the command-line interface: # Update a setting yolo settings runs_dir = '/path/to/runs' # Update multiple settings yolo settings runs_dir = '/path/to/runs' tensorboard = False # Reset settings to default values yolo settings reset Understanding Settings The table below overviews the adjustable settings within Ultralytics, including example values, data types, and descriptions. Name Example Value Data Type Description settings_version '0.0.4' str Ultralytics settings version (distinct from the Ultralytics pip version) datasets_dir '/path/to/datasets' str Directory where datasets are stored weights_dir '/path/to/weights' str Directory where model weights are stored runs_dir '/path/to/runs' str Directory where experiment runs are stored uuid 'a1b2c3d4' str Unique identifier for the current settings sync True bool Option to sync analytics and crashes to Ultralytics Platform api_key '' str Ultralytics Platform API Key clearml True bool Option to use ClearML logging comet True bool Option to use Comet ML for experiment tracking and visualization dvc True bool Option to use DVC for experiment tracking and version control hub True bool Option to use Ultralytics Platform integration mlflow True bool Option to use MLFlow for experiment tracking neptune True bool Option to use Neptune for experiment tracking raytune True bool Option to use Ray Tune for hyperparameter tuning tensorboard True bool Option to use TensorBoard for visualization wandb True bool Option to use Weights & Biases logging vscode_msg True bool When a VS Code terminal is detected, enables a prompt to download the Ultralytics-Snippets extension. Revisit these settings as you progress through projects or experiments to ensure optimal configuration. FAQ How do I install Ultralytics using pip? Install Ultralytics with pip using: pip install -U ultralytics This installs the latest stable release of the ultralytics package from PyPI . To install the development version directly from GitHub: pip install git+https://github.com/ultralytics/ultralytics.git Ensure the Git command-line tool is installed on your system. Can I install Ultralytics YOLO using conda? Yes, install Ultralytics YOLO using conda with: conda install -c conda-forge ultralytics This method is a great alternative to pip, ensuring compatibility with other packages. For CUDA environments, install ultralytics , pytorch , and pytorch-cuda together to resolve conflicts: conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda = 11 .8 ultralytics For more instructions, see the Conda quickstart guide . What are the advantages of using Docker to run Ultralytics YOLO? Docker provides an isolated, consistent environment for Ultralytics YOLO, ensuring smooth performance across systems and avoiding local installation complexities. Official Docker images are available on Docker Hub , with variants for GPU, CPU, ARM64, NVIDIA Jetson , and Conda. To pull and run the latest image: # Pull the latest ultralytics image from Docker Hub sudo docker pull ultralytics/ultralytics:latest # Run the ultralytics image in a container with GPU support sudo docker run -it --ipc = host --runtime = nvidia --gpus all ultralytics/ultralytics:latest For detailed Docker instructions, see the Docker quickstart guide . How do I clone the Ultralytics repository for development? Clone the Ultralytics repository and set up a development environment with: # Clone the ultralytics repository git clone https://github.com/ultralytics/ultralytics # Navigate to the cloned directory cd ultralytics # Install the package in editable mode for development pip install -e . This allows contributions to the project or experimentation with the latest source code. For details, visit the Ultralytics GitHub repository . Why should I use Ultralytics YOLO CLI? The Ultralytics YOLO CLI simplifies running object detection tasks without Python code, enabling single-line commands for training, validation, and prediction directly from your terminal. The basic syntax is: yolo TASK MODE ARGS For example, to train a detection model: yolo train data = coco8.yaml model = yolo26n.pt epochs = 10 lr0 = 0 .01 Explore more commands and usage examples in the full CLI Guide .
Markdown
[Skip to content](https://docs.ultralytics.com/quickstart/#install-ultralytics) [![Ultralytics](https://cdn.prod.website-files.com/680a070c3b99253410dd3dcf/680a070c3b99253410dd3e84_Ultralytics_full_white.svg) Introducing Ultralytics Platform: Annotate, train, and deploy YOLO models![Arrow](https://cdn.prod.website-files.com/680a070c3b99253410dd3dcf/69ba5bb596507e4235390de5_banner-arrow-right.png)](https://platform.ultralytics.com/) [![Ultralytics YOLO Docs](https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Reverse.svg)](https://www.ultralytics.com/ "Ultralytics YOLO Docs") Ultralytics YOLO Docs Install Ultralytics - [🇬🇧 English](https://docs.ultralytics.com/quickstart/) - [🇨🇳 简体中文](https://docs.ultralytics.com/zh/quickstart/) - [🇰🇷 한국어](https://docs.ultralytics.com/ko/quickstart/) - [🇯🇵 日本語](https://docs.ultralytics.com/ja/quickstart/) - [🇷🇺 Русский](https://docs.ultralytics.com/ru/quickstart/) - [🇩🇪 Deutsch](https://docs.ultralytics.com/de/quickstart/) - [🇫🇷 Français](https://docs.ultralytics.com/fr/quickstart/) - [🇪🇸 Español](https://docs.ultralytics.com/es/quickstart/) - [🇵🇹 Português](https://docs.ultralytics.com/pt/quickstart/) - [🇮🇹 Italiano](https://docs.ultralytics.com/it/quickstart/) - [🇹🇷 Türkçe](https://docs.ultralytics.com/tr/quickstart/) - [🇻🇳 Tiếng Việt](https://docs.ultralytics.com/vi/quickstart/) - [🇸🇦 العربية](https://docs.ultralytics.com/ar/quickstart/) Search Ctrl+K [ultralytics/ultralytics v8.4.33 55.4k 10.7k](https://github.com/ultralytics/ultralytics "Go to repository") - [Home](https://docs.ultralytics.com/) - [Modes](https://docs.ultralytics.com/modes/) - [Tasks](https://docs.ultralytics.com/tasks/) - [Models](https://docs.ultralytics.com/models/) - [Compare](https://docs.ultralytics.com/compare/) - [Datasets](https://docs.ultralytics.com/datasets/) - [Solutions](https://docs.ultralytics.com/solutions/) - [Guides](https://docs.ultralytics.com/guides/) - [Integrations](https://docs.ultralytics.com/integrations/) - [Platform](https://docs.ultralytics.com/platform/) - [Reference](https://docs.ultralytics.com/reference/__init__/) - [Help](https://docs.ultralytics.com/help/) [![Ultralytics YOLO Docs](https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Reverse.svg)](https://www.ultralytics.com/ "Ultralytics YOLO Docs") Ultralytics YOLO Docs [ultralytics/ultralytics v8.4.33 55.4k 10.7k](https://github.com/ultralytics/ultralytics "Go to repository") - [Home](https://docs.ultralytics.com/) Home - Quickstart [Quickstart](https://docs.ultralytics.com/quickstart/) On this page - [Conda Docker Image](https://docs.ultralytics.com/quickstart/#conda-docker-image) - [Headless Server Installation](https://docs.ultralytics.com/quickstart/#headless-server-installation) - [Advanced Installation](https://docs.ultralytics.com/quickstart/#advanced-installation) - [Use Ultralytics with CLI](https://docs.ultralytics.com/quickstart/#use-ultralytics-with-cli) - [Use Ultralytics with Python](https://docs.ultralytics.com/quickstart/#use-ultralytics-with-python) - [Ultralytics Settings](https://docs.ultralytics.com/quickstart/#ultralytics-settings) - [Inspecting Settings](https://docs.ultralytics.com/quickstart/#inspecting-settings) - [Modifying Settings](https://docs.ultralytics.com/quickstart/#modifying-settings) - [Understanding Settings](https://docs.ultralytics.com/quickstart/#understanding-settings) - [FAQ](https://docs.ultralytics.com/quickstart/#faq) - [How do I install Ultralytics using pip?](https://docs.ultralytics.com/quickstart/#how-do-i-install-ultralytics-using-pip) - [Can I install Ultralytics YOLO using conda?](https://docs.ultralytics.com/quickstart/#can-i-install-ultralytics-yolo-using-conda) - [What are the advantages of using Docker to run Ultralytics YOLO?](https://docs.ultralytics.com/quickstart/#what-are-the-advantages-of-using-docker-to-run-ultralytics-yolo) - [How do I clone the Ultralytics repository for development?](https://docs.ultralytics.com/quickstart/#how-do-i-clone-the-ultralytics-repository-for-development) - [Why should I use Ultralytics YOLO CLI?](https://docs.ultralytics.com/quickstart/#why-should-i-use-ultralytics-yolo-cli) - Usage Usage - [CLI](https://docs.ultralytics.com/usage/cli/) - [Python](https://docs.ultralytics.com/usage/python/) - [Callbacks](https://docs.ultralytics.com/usage/callbacks/) - [Configuration](https://docs.ultralytics.com/usage/cfg/) - [Simple Utilities](https://docs.ultralytics.com/usage/simple-utilities/) - [Advanced Customization](https://docs.ultralytics.com/usage/engine/) - [YOLO26 🚀](https://docs.ultralytics.com/models/yolo26/) - Languages Languages - [🇬🇧 English](https://ultralytics.com/docs/) - [🇨🇳 简体中文](https://docs.ultralytics.com/zh/) - [🇰🇷 한국어](https://docs.ultralytics.com/ko/) - [🇯🇵 日本語](https://docs.ultralytics.com/ja/) - [🇷🇺 Русский](https://docs.ultralytics.com/ru/) - [🇩🇪 Deutsch](https://docs.ultralytics.com/de/) - [🇫🇷 Français](https://docs.ultralytics.com/fr/) - [🇪🇸 Español](https://docs.ultralytics.com/es/) - [🇵🇹 Português](https://docs.ultralytics.com/pt/) - [🇮🇹 Italiano](https://docs.ultralytics.com/it/) - [🇹🇷 Türkçe](https://docs.ultralytics.com/tr/) - [🇻🇳 Tiếng Việt](https://docs.ultralytics.com/vi/) - [🇸🇦 العربية](https://docs.ultralytics.com/ar/) - [Ultralytics YOLO26 Modes](https://docs.ultralytics.com/modes/) - [Computer Vision Tasks Supported by Ultralytics YOLO26](https://docs.ultralytics.com/tasks/) - [Models Supported by Ultralytics](https://docs.ultralytics.com/models/) - [Model Comparisons: Choose the Best Object Detection Model for Your Project](https://docs.ultralytics.com/compare/) - [Datasets](https://docs.ultralytics.com/datasets/) - [Solutions](https://docs.ultralytics.com/solutions/) - [Guides](https://docs.ultralytics.com/guides/) - [Integrations](https://docs.ultralytics.com/integrations/) - [Platform](https://docs.ultralytics.com/platform/) - [Reference](https://docs.ultralytics.com/reference/__init__/) - [Help](https://docs.ultralytics.com/help/) On this page - [Conda Docker Image](https://docs.ultralytics.com/quickstart/#conda-docker-image) - [Headless Server Installation](https://docs.ultralytics.com/quickstart/#headless-server-installation) - [Advanced Installation](https://docs.ultralytics.com/quickstart/#advanced-installation) - [Use Ultralytics with CLI](https://docs.ultralytics.com/quickstart/#use-ultralytics-with-cli) - [Use Ultralytics with Python](https://docs.ultralytics.com/quickstart/#use-ultralytics-with-python) - [Ultralytics Settings](https://docs.ultralytics.com/quickstart/#ultralytics-settings) - [Inspecting Settings](https://docs.ultralytics.com/quickstart/#inspecting-settings) - [Modifying Settings](https://docs.ultralytics.com/quickstart/#modifying-settings) - [Understanding Settings](https://docs.ultralytics.com/quickstart/#understanding-settings) - [FAQ](https://docs.ultralytics.com/quickstart/#faq) - [How do I install Ultralytics using pip?](https://docs.ultralytics.com/quickstart/#how-do-i-install-ultralytics-using-pip) - [Can I install Ultralytics YOLO using conda?](https://docs.ultralytics.com/quickstart/#can-i-install-ultralytics-yolo-using-conda) - [What are the advantages of using Docker to run Ultralytics YOLO?](https://docs.ultralytics.com/quickstart/#what-are-the-advantages-of-using-docker-to-run-ultralytics-yolo) - [How do I clone the Ultralytics repository for development?](https://docs.ultralytics.com/quickstart/#how-do-i-clone-the-ultralytics-repository-for-development) - [Why should I use Ultralytics YOLO CLI?](https://docs.ultralytics.com/quickstart/#why-should-i-use-ultralytics-yolo-cli) # Install Ultralytics Ultralytics offers a variety of installation methods, including pip, conda, and Docker. You can install YOLO via the `ultralytics` pip package for the latest stable release, or by cloning the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) for the most current version. Docker is also an option to run the package in an isolated container, which avoids local installation. **Watch:** Ultralytics YOLO Quick Start Guide Install ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/ultralytics?logo=python&logoColor=gold) [Pip install (recommended)](https://docs.ultralytics.com/quickstart/#pip-install-recommended) [Conda install](https://docs.ultralytics.com/quickstart/#conda-install) [Git clone](https://docs.ultralytics.com/quickstart/#git-clone) [Docker](https://docs.ultralytics.com/quickstart/#docker) Install or update the `ultralytics` package using pip by running `pip install -U ultralytics`. For more details on the `ultralytics` package, visit the [Python Package Index (PyPI)](https://pypi.org/project/ultralytics/). [![PyPI - Version](https://img.shields.io/pypi/v/ultralytics?logo=pypi&logoColor=white)](https://pypi.org/project/ultralytics/)[![Downloads](https://static.pepy.tech/badge/ultralytics)](https://clickpy.clickhouse.com/dashboard/ultralytics) ``` ``` You can also install `ultralytics` directly from the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics). This can be useful if you want the latest development version. Ensure you have the Git command-line tool installed, and then run: ``` ``` Conda can be used as an alternative package manager to pip. For more details, visit [Anaconda](https://anaconda.org/conda-forge/ultralytics). The Ultralytics feedstock repository for updating the conda package is available at [GitHub](https://github.com/conda-forge/ultralytics-feedstock/). [![Conda Version](https://img.shields.io/conda/vn/conda-forge/ultralytics?logo=condaforge)](https://anaconda.org/conda-forge/ultralytics)[![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics)[![Conda Recipe](https://img.shields.io/badge/recipe-ultralytics-green.svg)](https://anaconda.org/conda-forge/ultralytics)[![Conda Platforms](https://img.shields.io/conda/pn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) ``` ``` Note If you are installing in a CUDA environment, it is best practice to install `ultralytics`, `pytorch`, and `pytorch-cuda` in the same command. This allows the conda package manager to resolve any conflicts. Alternatively, install `pytorch-cuda` last to override the CPU-specific `pytorch` package if necessary. ``` ``` ### Conda Docker Image Ultralytics Conda Docker images are also available on [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics). These images are based on [Miniconda3](https://www.anaconda.com/docs/main) and provide a straightforward way to start using `ultralytics` in a Conda environment. ``` ``` Clone the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) if you are interested in contributing to development or wish to experiment with the latest source code. After cloning, navigate into the directory and install the package in editable mode `-e` using pip. [![GitHub last commit](https://img.shields.io/github/last-commit/ultralytics/ultralytics?logo=github)](https://github.com/ultralytics/ultralytics)[![GitHub commit activity](https://img.shields.io/github/commit-activity/t/ultralytics/ultralytics)](https://github.com/ultralytics/ultralytics) ``` ``` Use Docker to execute the `ultralytics` package in an isolated container, ensuring consistent performance across various environments. By selecting one of the official `ultralytics` images from [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics), you avoid the complexity of local installation and gain access to a verified working environment. Ultralytics offers five main supported Docker images, each designed for high compatibility and efficiency: [![Docker Image Version](https://img.shields.io/docker/v/ultralytics/ultralytics?sort=semver&logo=docker)](https://hub.docker.com/r/ultralytics/ultralytics)[![Docker Pulls](https://img.shields.io/docker/pulls/ultralytics/ultralytics)](https://hub.docker.com/r/ultralytics/ultralytics) - **Dockerfile:** GPU image recommended for training. - **Dockerfile-arm64:** Optimized for ARM64 architecture, suitable for deployment on devices like Raspberry Pi and other ARM64-based platforms. - **Dockerfile-cpu:** Ubuntu-based CPU-only version, suitable for inference and environments without GPUs. - **Dockerfile-jetson:** Tailored for [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/) devices, integrating GPU support optimized for these platforms. - **Dockerfile-python:** Minimal image with just Python and necessary dependencies, ideal for lightweight applications and development. - **Dockerfile-conda:** Based on Miniconda3 with a conda installation of the `ultralytics` package. Here are the commands to get the latest image and execute it: ``` ``` The above command initializes a Docker container with the latest `ultralytics` image. The `-it` flags assign a pseudo-TTY and keep stdin open, allowing interaction with the container. The `--ipc=host` flag sets the IPC (Inter-Process Communication) namespace to the host, which is essential for sharing memory between processes. The `--gpus all` flag enables access to all available GPUs inside the container, crucial for tasks requiring GPU computation. Note: To work with files on your local machine within the container, use Docker volumes to mount a local directory into the container: ``` ``` Replace `/path/on/host` with the directory path on your local machine, and `/path/in/container` with the desired path inside the Docker container. For advanced Docker usage, explore the [Ultralytics Docker Guide](https://docs.ultralytics.com/guides/docker-quickstart/). See the `ultralytics` [pyproject.toml](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) file for a list of dependencies. Note that all examples above install all required dependencies. Tip [PyTorch](https://www.ultralytics.com/glossary/pytorch) requirements vary by operating system and CUDA requirements, so install PyTorch first by following the instructions at [PyTorch](https://pytorch.org/get-started/locally/). [![PyTorch installation selector for different platforms](https://cdn.jsdelivr.net/gh/ultralytics/assets@main/docs/pytorch-installation-instructions.avif)](https://pytorch.org/get-started/locally/) ## Headless Server Installation For server environments without a display (e.g., cloud VMs, Docker containers, CI/CD pipelines), use the `ultralytics-opencv-headless` package. This is identical to the standard `ultralytics` package but depends on `opencv-python-headless` instead of `opencv-python`, avoiding unnecessary GUI dependencies and potential `libGL` errors. Headless Install ``` pip install ultralytics-opencv-headless ``` Both packages provide the same functionality and API. The headless variant simply excludes OpenCV's GUI components that require display libraries. ## Advanced Installation While the standard installation methods cover most use cases, you might need a more tailored setup for development or custom configurations. Advanced Methods [Install from Fork](https://docs.ultralytics.com/quickstart/#install-from-fork) [Local Clone and Install](https://docs.ultralytics.com/quickstart/#local-clone-and-install) [Use requirements.txt](https://docs.ultralytics.com/quickstart/#use-requirementstxt) If you need persistent custom modifications, you can fork the Ultralytics repository, make changes to `pyproject.toml` or other code, and install from your fork. 1. **Fork** the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) to your own GitHub account. 2. **Clone** your fork locally: ``` ``` 3. **Create a new branch** for your changes: ``` git checkout -b my-custom-branch ``` 4. **Make your modifications** to `pyproject.toml` or other files as needed. 5. **Commit and push** your changes: ``` ``` 6. **Install** using pip with the `git+https` syntax, pointing to your branch: ``` pip install git+https://github.com/YOUR_USERNAME/ultralytics.git@my-custom-branch ``` Clone the repository locally, modify files as needed, and install in editable mode. 1. **Clone** the Ultralytics repository: ``` ``` 2. **Make your modifications** to `pyproject.toml` or other files as needed. 3. **Install** the package in editable mode (`-e`). Pip will use your modified `pyproject.toml` to resolve dependencies: ``` pip install -e . ``` This approach is useful for development or testing local changes before committing. Specify a custom Ultralytics fork in your `requirements.txt` file to ensure consistent installations across your team. requirements.txt ``` ``` Install dependencies from the file: ``` pip install -r requirements.txt ``` ## Use Ultralytics with CLI The Ultralytics command-line interface (CLI) allows for simple single-line commands without needing a Python environment. CLI requires no customization or Python code; run all tasks from the terminal with the `yolo` command. For more on using YOLO from the command line, see the [CLI Guide](https://docs.ultralytics.com/usage/cli/). Example [Syntax](https://docs.ultralytics.com/quickstart/#syntax) [Train](https://docs.ultralytics.com/quickstart/#train) [Predict](https://docs.ultralytics.com/quickstart/#predict) [Val](https://docs.ultralytics.com/quickstart/#val) [Export](https://docs.ultralytics.com/quickstart/#export) [Count](https://docs.ultralytics.com/quickstart/#count) [Workout](https://docs.ultralytics.com/quickstart/#workout) [Queue](https://docs.ultralytics.com/quickstart/#queue) [Inference with Streamlit](https://docs.ultralytics.com/quickstart/#inference-with-streamlit) [Special](https://docs.ultralytics.com/quickstart/#special) Ultralytics `yolo` commands use the following syntax: ``` yolo TASK MODE ARGS ``` \- `TASK` (optional) is one of ([detect](https://docs.ultralytics.com/tasks/detect/), [segment](https://docs.ultralytics.com/tasks/segment/), [classify](https://docs.ultralytics.com/tasks/classify/), [pose](https://docs.ultralytics.com/tasks/pose/), [obb](https://docs.ultralytics.com/tasks/obb/)) - `MODE` (required) is one of ([train](https://docs.ultralytics.com/modes/train/), [val](https://docs.ultralytics.com/modes/val/), [predict](https://docs.ultralytics.com/modes/predict/), [export](https://docs.ultralytics.com/modes/export/), [track](https://docs.ultralytics.com/modes/track/), [benchmark](https://docs.ultralytics.com/modes/benchmark/)) - `ARGS` (optional) are `arg=value` pairs like `imgsz=640` that override defaults. See all `ARGS` in the full [Configuration Guide](https://docs.ultralytics.com/usage/cfg/) or with the `yolo cfg` CLI command. Train a detection model for 10 [epochs](https://www.ultralytics.com/glossary/epoch) with an initial learning rate of 0.01: ``` yolo train data=coco8.yaml model=yolo26n.pt epochs=10 lr0=0.01 ``` Predict a YouTube video using a pretrained segmentation model at image size 320: ``` yolo predict model=yolo26n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 ``` Validate a pretrained detection model with a batch size of 1 and image size of 640: ``` yolo val model=yolo26n.pt data=coco8.yaml batch=1 imgsz=640 ``` Export a YOLO26n classification model to ONNX format with an image size of 224x128 (no TASK required): ``` yolo export model=yolo26n-cls.pt format=onnx imgsz=224,128 ``` Count objects in a video or live stream using YOLO26: ``` ``` Monitor workout exercises using a YOLO26 pose model: ``` ``` Use YOLO26 to count objects in a designated queue or region: ``` ``` Perform object detection, instance segmentation, or pose estimation in a web browser using [Streamlit](https://docs.ultralytics.com/reference/solutions/streamlit_inference/): ``` ``` Run special commands to see the version, view settings, run checks, and more: ``` ``` Warning Arguments must be passed as `arg=value` pairs, split by an equals `=` sign and delimited by spaces. Do not use `--` argument prefixes or commas `,` between arguments. - `yolo predict model=yolo26n.pt imgsz=640 conf=0.25` ✅ - `yolo predict model yolo26n.pt imgsz 640 conf 0.25` ❌ (missing `=`) - `yolo predict model=yolo26n.pt, imgsz=640, conf=0.25` ❌ (do not use `,`) - `yolo predict --model yolo26n.pt --imgsz 640 --conf 0.25` ❌ (do not use `--`) - `yolo solution model=yolo26n.pt imgsz=640 conf=0.25` ❌ (use `solutions`, not `solution`) [CLI Guide](https://docs.ultralytics.com/usage/cli/) ## Use Ultralytics with Python The Ultralytics YOLO Python interface offers seamless integration into Python projects, making it easy to load, run, and process model outputs. Designed for simplicity, the Python interface allows users to quickly implement [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification. This makes the YOLO Python interface an invaluable tool for incorporating these functionalities into Python projects. For instance, users can load a model, train it, evaluate its performance, and export it to ONNX format with just a few lines of code. Explore the [Python Guide](https://docs.ultralytics.com/usage/python/) to learn more about using YOLO within your Python projects. Example ``` ``` [Python Guide](https://docs.ultralytics.com/usage/python/) ## Ultralytics Settings The Ultralytics library includes a `SettingsManager` for fine-grained control over experiments, allowing users to access and modify settings easily. Stored in a JSON file within the environment's user configuration directory, these settings can be viewed or modified in the Python environment or via the Command-Line Interface (CLI). ### Inspecting Settings To view the current configuration of your settings: View settings [Python](https://docs.ultralytics.com/quickstart/#python) [CLI](https://docs.ultralytics.com/quickstart/#cli) Use Python to view your settings by importing the `settings` object from the `ultralytics` module. Print and return settings with these commands: ``` ``` The command-line interface allows you to check your settings with: ``` yolo settings ``` ### Modifying Settings Ultralytics makes it easy to modify settings in the following ways: Update settings [Python](https://docs.ultralytics.com/quickstart/#python_1) [CLI](https://docs.ultralytics.com/quickstart/#cli_1) In Python, use the `update` method on the `settings` object: ``` ``` To modify settings using the command-line interface: ``` ``` ### Understanding Settings The table below overviews the adjustable settings within Ultralytics, including example values, data types, and descriptions. | Name | Example Value | Data Type | Description | |---|---|---|---| | `settings_version` | `'0.0.4'` | `str` | Ultralytics *settings* version (distinct from the Ultralytics [pip](https://pypi.org/project/ultralytics/) version) | | `datasets_dir` | `'/path/to/datasets'` | `str` | Directory where datasets are stored | | `weights_dir` | `'/path/to/weights'` | `str` | Directory where model weights are stored | | `runs_dir` | `'/path/to/runs'` | `str` | Directory where experiment runs are stored | | `uuid` | `'a1b2c3d4'` | `str` | Unique identifier for the current settings | | `sync` | `True` | `bool` | Option to sync analytics and crashes to [Ultralytics Platform](https://platform.ultralytics.com/) | | `api_key` | `''` | `str` | [Ultralytics Platform](https://platform.ultralytics.com/) API Key | | `clearml` | `True` | `bool` | Option to use [ClearML](https://docs.ultralytics.com/integrations/clearml/) logging | | `comet` | `True` | `bool` | Option to use [Comet ML](https://bit.ly/yolov8-readme-comet) for experiment tracking and visualization | | `dvc` | `True` | `bool` | Option to use [DVC for experiment tracking](https://dvc.org/doc/dvclive/ml-frameworks/yolo) and version control | | `hub` | `True` | `bool` | Option to use [Ultralytics Platform](https://platform.ultralytics.com/) integration | | `mlflow` | `True` | `bool` | Option to use [MLFlow](https://docs.ultralytics.com/integrations/mlflow/) for experiment tracking | | `neptune` | `True` | `bool` | Option to use [Neptune](https://neptune.ai/) for experiment tracking | | `raytune` | `True` | `bool` | Option to use [Ray Tune](https://docs.ultralytics.com/integrations/ray-tune/) for [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) | | `tensorboard` | `True` | `bool` | Option to use [TensorBoard](https://docs.ultralytics.com/integrations/tensorboard/) for visualization | | `wandb` | `True` | `bool` | Option to use [Weights & Biases](https://docs.ultralytics.com/integrations/weights-biases/) logging | | `vscode_msg` | `True` | `bool` | When a VS Code terminal is detected, enables a prompt to download the [Ultralytics-Snippets](https://docs.ultralytics.com/integrations/vscode/) extension. | Revisit these settings as you progress through projects or experiments to ensure optimal configuration. ## FAQ ### How do I install Ultralytics using pip? Install Ultralytics with pip using: ``` pip install -U ultralytics ``` This installs the latest stable release of the `ultralytics` package from [PyPI](https://pypi.org/project/ultralytics/). To install the development version directly from GitHub: ``` pip install git+https://github.com/ultralytics/ultralytics.git ``` Ensure the Git command-line tool is installed on your system. ### Can I install Ultralytics YOLO using conda? Yes, install Ultralytics YOLO using conda with: ``` conda install -c conda-forge ultralytics ``` This method is a great alternative to pip, ensuring compatibility with other packages. For CUDA environments, install `ultralytics`, `pytorch`, and `pytorch-cuda` together to resolve conflicts: ``` conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics ``` For more instructions, see the [Conda quickstart guide](https://docs.ultralytics.com/guides/conda-quickstart/). ### What are the advantages of using Docker to run Ultralytics YOLO? Docker provides an isolated, consistent environment for Ultralytics YOLO, ensuring smooth performance across systems and avoiding local installation complexities. Official Docker images are available on [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics), with variants for GPU, CPU, ARM64, [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/), and Conda. To pull and run the latest image: ``` ``` For detailed Docker instructions, see the [Docker quickstart guide](https://docs.ultralytics.com/guides/docker-quickstart/). ### How do I clone the Ultralytics repository for development? Clone the Ultralytics repository and set up a development environment with: ``` ``` This allows contributions to the project or experimentation with the latest source code. For details, visit the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics). ### Why should I use Ultralytics YOLO CLI? The Ultralytics YOLO CLI simplifies running object detection tasks without Python code, enabling single-line commands for training, validation, and prediction directly from your terminal. The basic syntax is: ``` yolo TASK MODE ARGS ``` For example, to train a detection model: ``` yolo train data=coco8.yaml model=yolo26n.pt epochs=10 lr0=0.01 ``` Explore more commands and usage examples in the full [CLI Guide](https://docs.ultralytics.com/usage/cli/). 📅 Created 2 years ago ✏️ Updated 2 months ago [![glenn-jocher](https://avatars.githubusercontent.com/u/26833433?v=4&s=96)](https://github.com/glenn-jocher "glenn-jocher (26 changes)")[![RizwanMunawar](https://avatars.githubusercontent.com/u/62513924?v=4&s=96)](https://github.com/RizwanMunawar "RizwanMunawar (4 changes)")[![pderrenger](https://avatars.githubusercontent.com/u/107626595?v=4&s=96)](https://github.com/pderrenger "pderrenger (3 changes)")[![Burhan-Q](https://avatars.githubusercontent.com/u/62214284?v=4&s=96)](https://github.com/Burhan-Q "Burhan-Q (3 changes)")[![Laughing-q](https://avatars.githubusercontent.com/u/61612323?v=4&s=96)](https://github.com/Laughing-q "Laughing-q (2 changes)")[![onuralpszr](https://avatars.githubusercontent.com/u/1688848?v=4&s=96)](https://github.com/onuralpszr "onuralpszr (2 changes)")[![jk4e](https://avatars.githubusercontent.com/u/116908874?v=4&s=96)](https://github.com/jk4e "jk4e (2 changes)")[![RizwanMunawar](https://avatars.githubusercontent.com/u/62513924?v=4&s=96)](https://github.com/RizwanMunawar "RizwanMunawar (2 changes)")[![fcakyon](https://avatars.githubusercontent.com/u/34196005?v=4&s=96)](https://github.com/fcakyon "fcakyon (1 change)")[![lakshanthad](https://avatars.githubusercontent.com/u/20147381?v=4&s=96)](https://github.com/lakshanthad "lakshanthad (1 change)")[![picsalex](https://avatars.githubusercontent.com/u/132259399?v=4&s=96)](https://github.com/picsalex "picsalex (1 change)")[![leonnil](https://avatars.githubusercontent.com/u/146309319?v=4&s=96)](https://github.com/leonnil "leonnil (1 change)")[![MatthewNoyce](https://avatars.githubusercontent.com/u/131261051?v=4&s=96)](https://github.com/MatthewNoyce "MatthewNoyce (1 change)")[![UltralyticsAssistant](https://avatars.githubusercontent.com/u/135830346?v=4&s=96)](https://github.com/UltralyticsAssistant "UltralyticsAssistant (1 change)") Tweet Share ## Comments Back to top [Previous Home](https://docs.ultralytics.com/) [Next CLI](https://docs.ultralytics.com/usage/cli/) [© 2026 Ultralytics Inc.](https://www.ultralytics.com/) All rights reserved. Made with [Zensical](https://zensical.org/) Ask AI![Ultralytics AI](https://storage.googleapis.com/organization-image-assets/ultralytics-botAvatarSrcUrl-1729379860806.svg) [![Ultralytics AI](https://cdn.prod.website-files.com/680a070c3b99253410dd3dcf/68e4eb1e9893320b26cc02c3_Ultralytics%20Logo.png.svg)](https://www.ultralytics.com/) Ask anything about Ultralytics, YOLO, and more Hello 👋 Ask about YOLO, tutorials, training, export, deployment, or troubleshooting. What's new in SAM 3? How can I get started with YOLO26? How does Enterprise Licensing work? Search GitHub Powered by [Ultralytics Chat](https://github.com/ultralytics/llm)
Readable Markdown
Ultralytics offers a variety of installation methods, including pip, conda, and Docker. You can install YOLO via the `ultralytics` pip package for the latest stable release, or by cloning the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) for the most current version. Docker is also an option to run the package in an isolated container, which avoids local installation. **Watch:** Ultralytics YOLO Quick Start Guide Install ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/ultralytics?logo=python&logoColor=gold) Install or update the `ultralytics` package using pip by running `pip install -U ultralytics`. For more details on the `ultralytics` package, visit the [Python Package Index (PyPI)](https://pypi.org/project/ultralytics/). [![PyPI - Version](https://img.shields.io/pypi/v/ultralytics?logo=pypi&logoColor=white)](https://pypi.org/project/ultralytics/)[![Downloads](https://static.pepy.tech/badge/ultralytics)](https://clickpy.clickhouse.com/dashboard/ultralytics) ``` ``` You can also install `ultralytics` directly from the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics). This can be useful if you want the latest development version. Ensure you have the Git command-line tool installed, and then run: ``` ``` Conda can be used as an alternative package manager to pip. For more details, visit [Anaconda](https://anaconda.org/conda-forge/ultralytics). The Ultralytics feedstock repository for updating the conda package is available at [GitHub](https://github.com/conda-forge/ultralytics-feedstock/). [![Conda Version](https://img.shields.io/conda/vn/conda-forge/ultralytics?logo=condaforge)](https://anaconda.org/conda-forge/ultralytics)[![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics)[![Conda Recipe](https://img.shields.io/badge/recipe-ultralytics-green.svg)](https://anaconda.org/conda-forge/ultralytics)[![Conda Platforms](https://img.shields.io/conda/pn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) ``` ``` Note If you are installing in a CUDA environment, it is best practice to install `ultralytics`, `pytorch`, and `pytorch-cuda` in the same command. This allows the conda package manager to resolve any conflicts. Alternatively, install `pytorch-cuda` last to override the CPU-specific `pytorch` package if necessary. ``` ``` ### Conda Docker Image Ultralytics Conda Docker images are also available on [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics). These images are based on [Miniconda3](https://www.anaconda.com/docs/main) and provide a straightforward way to start using `ultralytics` in a Conda environment. ``` ``` Clone the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) if you are interested in contributing to development or wish to experiment with the latest source code. After cloning, navigate into the directory and install the package in editable mode `-e` using pip. [![GitHub last commit](https://img.shields.io/github/last-commit/ultralytics/ultralytics?logo=github)](https://github.com/ultralytics/ultralytics)[![GitHub commit activity](https://img.shields.io/github/commit-activity/t/ultralytics/ultralytics)](https://github.com/ultralytics/ultralytics) ``` ``` Use Docker to execute the `ultralytics` package in an isolated container, ensuring consistent performance across various environments. By selecting one of the official `ultralytics` images from [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics), you avoid the complexity of local installation and gain access to a verified working environment. Ultralytics offers five main supported Docker images, each designed for high compatibility and efficiency: [![Docker Image Version](https://img.shields.io/docker/v/ultralytics/ultralytics?sort=semver&logo=docker)](https://hub.docker.com/r/ultralytics/ultralytics)[![Docker Pulls](https://img.shields.io/docker/pulls/ultralytics/ultralytics)](https://hub.docker.com/r/ultralytics/ultralytics) - **Dockerfile:** GPU image recommended for training. - **Dockerfile-arm64:** Optimized for ARM64 architecture, suitable for deployment on devices like Raspberry Pi and other ARM64-based platforms. - **Dockerfile-cpu:** Ubuntu-based CPU-only version, suitable for inference and environments without GPUs. - **Dockerfile-jetson:** Tailored for [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/) devices, integrating GPU support optimized for these platforms. - **Dockerfile-python:** Minimal image with just Python and necessary dependencies, ideal for lightweight applications and development. - **Dockerfile-conda:** Based on Miniconda3 with a conda installation of the `ultralytics` package. Here are the commands to get the latest image and execute it: ``` ``` The above command initializes a Docker container with the latest `ultralytics` image. The `-it` flags assign a pseudo-TTY and keep stdin open, allowing interaction with the container. The `--ipc=host` flag sets the IPC (Inter-Process Communication) namespace to the host, which is essential for sharing memory between processes. The `--gpus all` flag enables access to all available GPUs inside the container, crucial for tasks requiring GPU computation. Note: To work with files on your local machine within the container, use Docker volumes to mount a local directory into the container: ``` ``` Replace `/path/on/host` with the directory path on your local machine, and `/path/in/container` with the desired path inside the Docker container. For advanced Docker usage, explore the [Ultralytics Docker Guide](https://docs.ultralytics.com/guides/docker-quickstart/). See the `ultralytics` [pyproject.toml](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) file for a list of dependencies. Note that all examples above install all required dependencies. Tip [PyTorch](https://www.ultralytics.com/glossary/pytorch) requirements vary by operating system and CUDA requirements, so install PyTorch first by following the instructions at [PyTorch](https://pytorch.org/get-started/locally/). [![PyTorch installation selector for different platforms](https://cdn.jsdelivr.net/gh/ultralytics/assets@main/docs/pytorch-installation-instructions.avif)](https://pytorch.org/get-started/locally/) ## Headless Server Installation For server environments without a display (e.g., cloud VMs, Docker containers, CI/CD pipelines), use the `ultralytics-opencv-headless` package. This is identical to the standard `ultralytics` package but depends on `opencv-python-headless` instead of `opencv-python`, avoiding unnecessary GUI dependencies and potential `libGL` errors. Headless Install ``` pip install ultralytics-opencv-headless ``` Both packages provide the same functionality and API. The headless variant simply excludes OpenCV's GUI components that require display libraries. ## Advanced Installation While the standard installation methods cover most use cases, you might need a more tailored setup for development or custom configurations. Advanced Methods If you need persistent custom modifications, you can fork the Ultralytics repository, make changes to `pyproject.toml` or other code, and install from your fork. 1. **Fork** the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) to your own GitHub account. 2. **Clone** your fork locally: ``` ``` 3. **Create a new branch** for your changes: ``` git checkout -b my-custom-branch ``` 4. **Make your modifications** to `pyproject.toml` or other files as needed. 5. **Commit and push** your changes: ``` ``` 6. **Install** using pip with the `git+https` syntax, pointing to your branch: ``` pip install git+https://github.com/YOUR_USERNAME/ultralytics.git@my-custom-branch ``` Clone the repository locally, modify files as needed, and install in editable mode. 1. **Clone** the Ultralytics repository: ``` ``` 2. **Make your modifications** to `pyproject.toml` or other files as needed. 3. **Install** the package in editable mode (`-e`). Pip will use your modified `pyproject.toml` to resolve dependencies: ``` pip install -e . ``` This approach is useful for development or testing local changes before committing. Specify a custom Ultralytics fork in your `requirements.txt` file to ensure consistent installations across your team. requirements.txt ``` ``` Install dependencies from the file: ``` pip install -r requirements.txt ``` ## Use Ultralytics with CLI The Ultralytics command-line interface (CLI) allows for simple single-line commands without needing a Python environment. CLI requires no customization or Python code; run all tasks from the terminal with the `yolo` command. For more on using YOLO from the command line, see the [CLI Guide](https://docs.ultralytics.com/usage/cli/). Example Train a detection model for 10 [epochs](https://www.ultralytics.com/glossary/epoch) with an initial learning rate of 0.01: ``` yolo train data=coco8.yaml model=yolo26n.pt epochs=10 lr0=0.01 ``` Predict a YouTube video using a pretrained segmentation model at image size 320: ``` yolo predict model=yolo26n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 ``` Validate a pretrained detection model with a batch size of 1 and image size of 640: ``` yolo val model=yolo26n.pt data=coco8.yaml batch=1 imgsz=640 ``` Export a YOLO26n classification model to ONNX format with an image size of 224x128 (no TASK required): ``` yolo export model=yolo26n-cls.pt format=onnx imgsz=224,128 ``` Count objects in a video or live stream using YOLO26: ``` ``` Monitor workout exercises using a YOLO26 pose model: ``` ``` Use YOLO26 to count objects in a designated queue or region: ``` ``` Perform object detection, instance segmentation, or pose estimation in a web browser using [Streamlit](https://docs.ultralytics.com/reference/solutions/streamlit_inference/): ``` ``` Run special commands to see the version, view settings, run checks, and more: ``` ``` Warning Arguments must be passed as `arg=value` pairs, split by an equals `=` sign and delimited by spaces. Do not use `--` argument prefixes or commas `,` between arguments. - `yolo predict model=yolo26n.pt imgsz=640 conf=0.25` ✅ - `yolo predict model yolo26n.pt imgsz 640 conf 0.25` ❌ (missing `=`) - `yolo predict model=yolo26n.pt, imgsz=640, conf=0.25` ❌ (do not use `,`) - `yolo predict --model yolo26n.pt --imgsz 640 --conf 0.25` ❌ (do not use `--`) - `yolo solution model=yolo26n.pt imgsz=640 conf=0.25` ❌ (use `solutions`, not `solution`) [CLI Guide](https://docs.ultralytics.com/usage/cli/) ## Use Ultralytics with Python The Ultralytics YOLO Python interface offers seamless integration into Python projects, making it easy to load, run, and process model outputs. Designed for simplicity, the Python interface allows users to quickly implement [object detection](https://www.ultralytics.com/glossary/object-detection), segmentation, and classification. This makes the YOLO Python interface an invaluable tool for incorporating these functionalities into Python projects. For instance, users can load a model, train it, evaluate its performance, and export it to ONNX format with just a few lines of code. Explore the [Python Guide](https://docs.ultralytics.com/usage/python/) to learn more about using YOLO within your Python projects. Example ``` ``` [Python Guide](https://docs.ultralytics.com/usage/python/) ## Ultralytics Settings The Ultralytics library includes a `SettingsManager` for fine-grained control over experiments, allowing users to access and modify settings easily. Stored in a JSON file within the environment's user configuration directory, these settings can be viewed or modified in the Python environment or via the Command-Line Interface (CLI). ### Inspecting Settings To view the current configuration of your settings: View settings Use Python to view your settings by importing the `settings` object from the `ultralytics` module. Print and return settings with these commands: ``` ``` The command-line interface allows you to check your settings with: ``` yolo settings ``` ### Modifying Settings Ultralytics makes it easy to modify settings in the following ways: Update settings In Python, use the `update` method on the `settings` object: ``` ``` To modify settings using the command-line interface: ``` ``` ### Understanding Settings The table below overviews the adjustable settings within Ultralytics, including example values, data types, and descriptions. | Name | Example Value | Data Type | Description | |---|---|---|---| | `settings_version` | `'0.0.4'` | `str` | Ultralytics *settings* version (distinct from the Ultralytics [pip](https://pypi.org/project/ultralytics/) version) | | `datasets_dir` | `'/path/to/datasets'` | `str` | Directory where datasets are stored | | `weights_dir` | `'/path/to/weights'` | `str` | Directory where model weights are stored | | `runs_dir` | `'/path/to/runs'` | `str` | Directory where experiment runs are stored | | `uuid` | `'a1b2c3d4'` | `str` | Unique identifier for the current settings | | `sync` | `True` | `bool` | Option to sync analytics and crashes to [Ultralytics Platform](https://platform.ultralytics.com/) | | `api_key` | `''` | `str` | [Ultralytics Platform](https://platform.ultralytics.com/) API Key | | `clearml` | `True` | `bool` | Option to use [ClearML](https://docs.ultralytics.com/integrations/clearml/) logging | | `comet` | `True` | `bool` | Option to use [Comet ML](https://bit.ly/yolov8-readme-comet) for experiment tracking and visualization | | `dvc` | `True` | `bool` | Option to use [DVC for experiment tracking](https://dvc.org/doc/dvclive/ml-frameworks/yolo) and version control | | `hub` | `True` | `bool` | Option to use [Ultralytics Platform](https://platform.ultralytics.com/) integration | | `mlflow` | `True` | `bool` | Option to use [MLFlow](https://docs.ultralytics.com/integrations/mlflow/) for experiment tracking | | `neptune` | `True` | `bool` | Option to use [Neptune](https://neptune.ai/) for experiment tracking | | `raytune` | `True` | `bool` | Option to use [Ray Tune](https://docs.ultralytics.com/integrations/ray-tune/) for [hyperparameter tuning](https://www.ultralytics.com/glossary/hyperparameter-tuning) | | `tensorboard` | `True` | `bool` | Option to use [TensorBoard](https://docs.ultralytics.com/integrations/tensorboard/) for visualization | | `wandb` | `True` | `bool` | Option to use [Weights & Biases](https://docs.ultralytics.com/integrations/weights-biases/) logging | | `vscode_msg` | `True` | `bool` | When a VS Code terminal is detected, enables a prompt to download the [Ultralytics-Snippets](https://docs.ultralytics.com/integrations/vscode/) extension. | Revisit these settings as you progress through projects or experiments to ensure optimal configuration. ## FAQ ### How do I install Ultralytics using pip? Install Ultralytics with pip using: ``` pip install -U ultralytics ``` This installs the latest stable release of the `ultralytics` package from [PyPI](https://pypi.org/project/ultralytics/). To install the development version directly from GitHub: ``` pip install git+https://github.com/ultralytics/ultralytics.git ``` Ensure the Git command-line tool is installed on your system. ### Can I install Ultralytics YOLO using conda? Yes, install Ultralytics YOLO using conda with: ``` conda install -c conda-forge ultralytics ``` This method is a great alternative to pip, ensuring compatibility with other packages. For CUDA environments, install `ultralytics`, `pytorch`, and `pytorch-cuda` together to resolve conflicts: ``` conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics ``` For more instructions, see the [Conda quickstart guide](https://docs.ultralytics.com/guides/conda-quickstart/). ### What are the advantages of using Docker to run Ultralytics YOLO? Docker provides an isolated, consistent environment for Ultralytics YOLO, ensuring smooth performance across systems and avoiding local installation complexities. Official Docker images are available on [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics), with variants for GPU, CPU, ARM64, [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/), and Conda. To pull and run the latest image: ``` ``` For detailed Docker instructions, see the [Docker quickstart guide](https://docs.ultralytics.com/guides/docker-quickstart/). ### How do I clone the Ultralytics repository for development? Clone the Ultralytics repository and set up a development environment with: ``` ``` This allows contributions to the project or experimentation with the latest source code. For details, visit the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics). ### Why should I use Ultralytics YOLO CLI? The Ultralytics YOLO CLI simplifies running object detection tasks without Python code, enabling single-line commands for training, validation, and prediction directly from your terminal. The basic syntax is: ``` yolo TASK MODE ARGS ``` For example, to train a detection model: ``` yolo train data=coco8.yaml model=yolo26n.pt epochs=10 lr0=0.01 ``` Explore more commands and usage examples in the full [CLI Guide](https://docs.ultralytics.com/usage/cli/).
Shard133 (laksa)
Root Hash10189578256822373533
Unparsed URLcom,ultralytics!docs,/quickstart/ s443