### Run X-AnyLabeling Application

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Execute this command to start the X-AnyLabeling application after successful installation and verification.

```bash
xanylabeling
```

--------------------------------

### Install X-AnyLabeling Dependencies

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/detection/hbb/README.md

Clone the X-AnyLabeling repository and navigate to its directory to install the necessary dependencies for version 2.5.0 or higher. Refer to the installation guide for further steps.

```bash
cd ..
git clone https://github.com/CVHub520/X-AnyLabeling
cd X-AnyLabeling
```

--------------------------------

### Install Dependencies from Source for CPU

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install X-AnyLabeling dependencies in developer mode for CPU support after cloning the repository. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CPU [Windows/Linux/macOS]
uv pip install -e ".[cpu]"
```

--------------------------------

### Install X-AnyLabeling Pip Package for CPU

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install the latest beta pre-release of X-AnyLabeling for CPU support using uv pip. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CPU [Windows/Linux/macOS]
uv pip install --pre "x-anylabeling-cvhub[cpu]"
```

--------------------------------

### Install GroundingDINO Dependencies and Build

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/detection/hbb/README.md

Install project dependencies, set the GCC compiler to version 11, and then build and install the GroundingDINO ops. Run the test script afterwards.

```bash
pip install -r requirements.txt
export CC=/usr/bin/gcc-11  # Ensure GCC 11 is used for compilation
cd models/GroundingDINO/ops
python setup.py build install
python test.py
```

--------------------------------

### Start X-AnyLabeling-Server

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/grounding/locateanything/README.md

Start the X-AnyLabeling-Server using uvicorn. Ensure the server is accessible on the specified host and port.

```bash
uvicorn app.main:app --host 0.0.0.0 --port 8000
```

--------------------------------

### Show Detailed Help for a Specific Task

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Use this command to get detailed information and examples for a particular conversion task, such as 'yolo2xlabel'.

```bash
xanylabeling convert --task yolo2xlabel
```

--------------------------------

### Show Help for a Specific Conversion Task

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Use this command to get detailed help and examples for a specific conversion task, such as 'xlabel2yolo'.

```bash
xanylabeling convert <task>
```

--------------------------------

### Clone and Install X-AnyLabeling

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/grounding/yoloe/README.md

Clone the X-AnyLabeling repository and install its dependencies. This should be done in the same environment as YOLOE.

```bash
cd ..
git clone https://github.com/CVHub520/X-AnyLabeling.git
cd X-AnyLabeling
pip install -r requirements.txt
```

--------------------------------

### Install Dependencies from Source for GPU (CUDA 11.x)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install X-AnyLabeling dependencies in developer mode for CUDA 11.x GPU support after cloning the repository. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CUDA 11.x [Windows/Linux]
uv pip install -e ".[gpu-cu11]"
```

--------------------------------

### Install X-AnyLabeling with Dev Dependencies

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Use this command to install X-AnyLabeling along with development dependencies for secondary development or package compilation. Ensure you are in the project directory.

```bash
uv pip install -e ".[cpu,dev]"
```

--------------------------------

### Install X-AnyLabeling Pip Package for GPU (CUDA 11.x)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install the latest beta pre-release of X-AnyLabeling for CUDA 11.x GPU support using uv pip. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CUDA 11.x [Windows/Linux]
uv pip install --pre "x-anylabeling-cvhub[gpu-cu11]"
```

--------------------------------

### Clone Repository and Install Dependencies

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/training/ultralytics/README.md

Clone the X-AnyLabeling repository and install its dependencies using uv, selecting the appropriate requirements file for your system (e.g., GPU, CPU, macOS).

```bash
git clone https://github.com/CVHub520/X-AnyLabeling.git
cd X-AnyLabeling
# Replace [suffix] with your choice, e.g., gpu-dev
uv pip install -r requirements-[suffix].txt
```

--------------------------------

### Install Dependencies from Source for GPU (CUDA 12.x)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install X-AnyLabeling dependencies in developer mode for CUDA 12.x GPU support after cloning the repository. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CUDA 12.x is the default GPU option [Windows/Linux]
uv pip install -e ".[gpu]"
```

--------------------------------

### Install Ultralytics with uv

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/training/ultralytics/README.md

Install or upgrade the uv package manager and then install the Ultralytics library using uv, with automatic PyTorch backend detection.

```bash
pip install --upgrade uv
uv pip install ultralytics --torch-backend=auto
```

--------------------------------

### Install SAM2

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/interactive_video_object_segmentation/sam2/README.md

Clone the SAM2 repository and install it as an editable package. Ensure PyTorch and TorchVision are installed with compatible versions.

```bash
git clone https://github.com/CVHub520/segment-anything-2
cd segment-anything-2
pip install -e .
```

--------------------------------

### Install X-AnyLabeling Pip Package for GPU (CUDA 12.x)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install the latest beta pre-release of X-AnyLabeling for CUDA 12.x GPU support using uv pip. Ensure uv is installed and the environment is activated.

```bash
pip install -U uv

# CUDA 12.x is the default GPU option [Windows/Linux]
uv pip install --pre "x-anylabeling-cvhub[gpu]"
```

--------------------------------

### Launch X-AnyLabeling App

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/interactive_video_object_segmentation/sam2/README.md

Start the X-AnyLabeling application. This command launches the main interface for labeling tasks.

```bash
python3 anylabeling/app.py
```

--------------------------------

### Install ChatRex and UPN Dependencies

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/detection/hbb/README.md

Clone the ChatRex repository and install it along with its specific dependencies for the Universal Proposal Network (UPN). This includes installing deformable attention for UPN.

```bash
git clone https://github.com/IDEA-Research/ChatRex.git
cd ChatRex
pip install -v -e .
# install deformable attention for universal proposal network
cd chatrex/upn/ops
pip install -v -e .
# Back to the project root directory
cd -
```

--------------------------------

### Install Flash Attention

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/optical_character_recognition/multi_task/README.md

Install flash-attn to improve performance and reduce memory usage during inference. This is a recommended step for optimal performance.

```bash
pip install flash-attn --no-build-isolation
```

--------------------------------

### Run X-AnyLabeling Application

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/classification/shape-level/README.md

Execute the X-AnyLabeling application from the command line. This is the primary step to start the annotation tool.

```bash
python anylabeling/app.py

```

--------------------------------

### Depth Anything V2 Example Configuration

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/estimation/depth_estimation/README.md

Example configuration for the Depth Anything V2 model, including calibration parameters. Ensure min_depth and max_depth are set appropriately for your scene.

```yaml
type: depth_anything_v2
name: depth_anything_v2_vit_b
display_name: Depth-Anything-V2-Base
model_path: depth_anything_v2_vitb.onnx
render_mode: color
min_depth: 1.0
max_depth: 50.0
save_raw_depth: true
```

--------------------------------

### Install LocateAnything with UV

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/grounding/locateanything/README.md

Install LocateAnything and its dependencies using pip with the uv package manager. Ensure you are in a dedicated environment to manage transformer version conflicts.

```bash
conda activate locateanything
cd /path/to/X-AnyLabeling-Server

pip install --upgrade uv
uv pip install -e .[locateanything]
```

--------------------------------

### Install Transformers Development Branch

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/optical_character_recognition/document_layout_analysis/README.md

Install the latest development branch of the transformers library, which is a requirement for PP-DocLayoutV3. Ensure you are using a compatible version of X-AnyLabeling Server and client.

```bash
pip install --upgrade git+https://github.com/huggingface/transformers.git
```

--------------------------------

### Run AnyLabeling Application

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/classification/image-level/README.md

Execute the AnyLabeling application from the command line. This command starts the application, allowing for subsequent configuration via the GUI.

```bash
python anylabeling/app.py
```

--------------------------------

### Display Application Version

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Run the 'version' command to get the current version number of the X-AnyLabeling application.

```bash
xanylabeling version
```

--------------------------------

### AI Auto Segmentation JSON Output Example

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/video_classifier.md

The AI model is expected to return JSON data containing events with start time, end time, and a description. Ensure start_time and end_time are in HH:mm:ss format.

```json
{
  "events": [
    {
      "start_time": "00:00:00",
      "end_time": "00:00:05",
      "event": "The person walks toward the table holding a box and places the box on the table."
    }
  ]
}
```

--------------------------------

### Start X-AnyLabeling Using Label and Label Flags Files

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/classification/shape-level/README.md

Initiate X-AnyLabeling by referencing external files for labels and label flags. This approach is useful for managing complex label configurations.

```bash
python anylabeling/app.py --labels labels.txt --labelflags label_flags.yaml --validatelabel exact

```

--------------------------------

### Install Transformers Package

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/vision_language/florence2/README.md

Install the transformers package using pip. Ensure PyTorch and TorchVision are installed separately according to their official instructions.

```bash
pip install transformers
```

--------------------------------

### Display Configuration File Path

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Use the 'config' command to find the path to the X-AnyLabeling configuration file.

```bash
xanylabeling config
```

--------------------------------

### Display X-AnyLabeling Help Information

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Use this command to view all available command-line options and their descriptions.

```bash
xanylabeling help
```

--------------------------------

### Run X-AnyLabeling with XCB Platform Plugin

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

For Fedora KDE users experiencing slow mouse movement or response lag, launch X-AnyLabeling with the --qt-platform xcb parameter to potentially improve performance.

```bash
xanylabeling --qt-platform xcb
```

--------------------------------

### Launch GUI

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Launches the X-AnyLabeling GUI. Use options to specify files, directories, output paths, configuration files, logging levels, disable updates, or adjust image allocation limits.

```bash
xanylabeling
```

```bash
xanylabeling --filename /path/to/image.jpg
```

```bash
xanylabeling --filename /path/to/folder
```

```bash
xanylabeling --output /path/to/output
```

```bash
xanylabeling --config /path/to/config.yaml
```

```bash
xanylabeling --logger-level debug
```

```bash
xanylabeling --no-auto-update-check
```

```bash
xanylabeling --qt-image-allocation-limit 1024
```

--------------------------------

### Quick Start with Command Line Flags

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/classification/image-level/README.md

Launch AnyLabeling directly from the command line, specifying image classification labels as a comma-separated string. Ensure labels are separated by commas.

```bash
python anylabeling/app.py --flags Apple,Meta,Google
```

--------------------------------

### Install Transformers Library

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/optical_character_recognition/multi_task/README.md

Install the required transformers library version for PaddleOCR-VL-1.5. Ensure you are using transformers>=5.0.0.

```bash
python -m pip install "transformers>=5.0.0"
```

--------------------------------

### Load Flags from a Configuration File via Command Line

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/classification/image-level/README.md

Start AnyLabeling using a configuration file that lists categories, with each category on a new line. This method is useful for managing a larger number of labels.

```bash
python anylabeling/app.py --flags flags.txt
```

--------------------------------

### Install PyQt Dependencies on macOS

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/training/ultralytics/README.md

For macOS users, install specific PyQt versions and pyqtwebengine from conda-forge using conda.

```bash
conda install -c conda-forge pyqt==5.15.9 pyqtwebengine
```

--------------------------------

### Clone and Install YOLOE Repository

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/grounding/yoloe/README.md

Clone the YOLOE repository from GitHub and install its dependencies using the provided requirements file.

```bash
git clone https://github.com/THU-MIG/yoloe.git
cd yoloe
pip install -r requirements.txt
```

--------------------------------

### Run YOLO to XLABEL Conversion (Detection Mode)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Example of running the 'yolo2xlabel' conversion task in 'detect' mode. Ensure you provide paths to images, labels, output directory, and a classes file.

```bash
xanylabeling convert --task yolo2xlabel --mode detect --images ./images --labels ./labels \
    --output ./output --classes classes.txt
```

--------------------------------

### Install uv Package Manager

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/get_started.md

Install the uv package manager using a curl script for Linux/macOS/WSL2 or a PowerShell command for Windows.

```bash
# Linux / macOS / WSL2
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Install PyTorch with CUDA 12.1 Support

Source: https://github.com/cvhub520/x-anylabeling/blob/main/examples/detection/hbb/README.md

Install specific versions of PyTorch, Torchvision, and Torchaudio compatible with CUDA 12.1. This is crucial for GPU acceleration.

```bash
pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121
```

--------------------------------

### Install TensorRT and CUDA Python Dependencies

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/zh_cn/custom_model.md

Install necessary libraries for NVIDIA TensorRT inference within your Python environment. Use 'pip' if not using 'uv'.

```bash
uv pip install tensorrt cuda-python
```

--------------------------------

### Display Help Information

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Use the --help flag to display comprehensive help information for the X-AnyLabeling CLI, including all available commands and options.

```bash
xanylabeling --help
```

--------------------------------

### Run YOLO to XLABEL Conversion (Pose Mode)

Source: https://github.com/cvhub520/x-anylabeling/blob/main/docs/en/cli.md

Example of converting YOLO format to XLABEL for 'pose' estimation. Requires paths to images, labels, output, and a pose configuration file.

```bash
xanylabeling convert --task yolo2xlabel --mode pose --images ./images --labels ./labels \
    --output ./output --pose-cfg pose_config.yaml
```