### Complete Deployment Steps Example

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.en.md

A consolidated example showing the sequence of commands to install the service, start the OCR service, and then call it using a Python script.

```bash
# Install the service deployment plugin
paddlex --install serving
# Start the service
paddlex --serve --pipeline OCR
# Call the service | The code in fast_test.py is a Python calling example from the previous section
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png -O demo.jpg
python fast_test.py
```

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

### Server Startup Output Example

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_deploy/serving.en.md

Example output observed when the PaddleX serving server starts successfully, indicating the GRPC, HTTP, and Metrics services are running.

```text
I1216 11:37:21.601943 35 grpc_server.cc:4117] Started GRPCInferenceService at 0.0.0.0:8001
I1216 11:37:21.602333 35 http_server.cc:2815] Started HTTPService at 0.0.0.0:8000
I1216 11:37:21.643494 35 http_server.cc:167] Started Metrics Service at 0.0.0.0:8002
```

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

### Full Deployment Steps

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.md

A consolidated list of commands to install the serving plugin, start the service, and invoke it. This provides a quick end-to-end deployment workflow.

```bash
# 安装服务化部署插件
paddlex --install serving
# 启动服务
paddlex --serve --pipeline OCR
# 调用服务 | fast_test.py 中代码为上一节的 Python 调用示例
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png -O demo.jpg
python fast_test.py
```

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

### Quick Start Instance Segmentation Pipeline

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/instance_segmentation_remote_sensing_tutorial.en.md

Initiates a quick trial of the instance segmentation pipeline using a specified input image. Ensure PaddleX is installed and accessible in your environment.

```bash
paddlex --pipeline instance_segmentation \
    --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/remotesensing_demo.png
```

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

### PaddleOCR-VL Server Startup Information

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/ocr_pipelines/PaddleOCR-VL.en.md

Example output indicating that the PaddleOCR-VL server has started successfully and is listening on a specific address and port.

```text
INFO:     Started server process [63108]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
```

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

### Install Serving Plugin

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_deploy/serving.en.md

Install the serving plugin using the paddlex CLI.

```bash
paddlex --install serving
```

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

### Install Ascend Initialization Script

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/deploy/ultra-infer/CMakeLists.txt

Installs the ascend_init.sh script to the installation prefix if WITH_ASCEND is enabled.

```cmake
if(WITH_ASCEND)
  install(
    FILES ${PROJECT_SOURCE_DIR}/scripts/ascend_init.sh
    DESTINATION ${CMAKE_INSTALL_PREFIX}
  )
endif()
```

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

### Install Project License and Configuration Files

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/deploy/ultra-infer/CMakeLists.txt

Installs project license, version, and CMake configuration files to the installation prefix.

```cmake
install(
  FILES
  ${PROJECT_SOURCE_DIR}/LICENSE
  ${PROJECT_SOURCE_DIR}/ThirdPartyNotices.txt
  ${PROJECT_SOURCE_DIR}/VERSION_NUMBER
  ${PROJECT_SOURCE_DIR}/UltraInfer.cmake
  ${PROJECT_SOURCE_DIR}/UltraInferCSharp.cmake
  ${PROJECT_SOURCE_DIR}/cmake/UltraInferConfig.cmake
  ${PROJECT_SOURCE_DIR}/cmake/utils.cmake
  ${PROJECT_SOURCE_DIR}/cmake/summary.cmake
  DESTINATION ${CMAKE_INSTALL_PREFIX}
)
```

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

### Install Initialization Script (Non-Windows)

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/deploy/ultra-infer/CMakeLists.txt

Installs the ultra_infer_init.sh script to the installation prefix on non-Windows systems.

```cmake
if(NOT WIN32)
  install(
    FILES ${PROJECT_SOURCE_DIR}/scripts/ultra_infer_init.sh
    DESTINATION ${CMAKE_INSTALL_PREFIX}
  )
else()
  install(
    FILES ${PROJECT_SOURCE_DIR}/scripts/ultra_infer_init.bat
    DESTINATION ${CMAKE_INSTALL_PREFIX}
  )
endif()
```

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

### Install All PaddleX Plugins

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/installation/installation.en.md

Installs all available PaddleX plugins. This is a convenient option when all functionalities are needed.

```bash
paddlex --install
```

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

### Start Service with OCR Pipeline

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.md

Start a service using the PaddleX CLI with a specified pipeline. This example uses the general OCR pipeline.

```bash
paddlex --serve --pipeline OCR
```

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

### Install PaddleX with Base Dependencies

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/installation/installation.en.md

Installs the PaddleX wheel package along with essential dependencies for basic features. Use this for a more complete setup.

```bash
pip install "paddlex[base]"
```

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

### Include Examples Subdirectory

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/deploy/ultra-infer/CMakeLists.txt

Includes the examples subdirectory if BUILD_EXAMPLES is enabled and the directory exists. Sets executable output path if necessary.

```cmake
if(BUILD_EXAMPLES AND EXISTS ${PROJECT_SOURCE_DIR}/examples)
  add_definitions(-DBUILD_EXAMPLES)
  if(NOT EXECUTABLE_OUTPUT_PATH STREQUAL ${CMAKE_CURRENT_BINARY_DIR}/bin)
    set(EXECUTABLE_OUTPUT_PATH ${CMAKE_CURRENT_BINARY_DIR}/bin)
  endif()
  include(${PROJECT_SOURCE_DIR}/cmake/gflags.cmake)
  add_subdirectory(examples)
endif()
```

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

### Start Service with Object Detection Pipeline

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.md

Demonstrates starting a service with a different pipeline, specifically the general object detection pipeline. This shows flexibility in choosing deployment targets.

```bash
paddlex --serve --pipeline object_detection
```

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

### Get PaddleOCR-VL Pipeline Configuration

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/ocr_pipelines/PaddleOCR-VL.en.md

Obtain the default pipeline configuration file for PaddleOCR-VL. This file will need to be modified to match your service setup.

```bash
paddlex --get_pipeline_config PaddleOCR-VL-1.6
```

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

### Run Basic Serving Server

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_deploy/serving.en.md

Start the serving server using the paddlex CLI, specifying the pipeline name or configuration file path.

```bash
paddlex --serve --pipeline {pipeline name or path to pipeline config file} [{other commandline options}]
```

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

### Instance Segmentation Command Line Example

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/index.en.md

Run instance segmentation by specifying the pipeline, input, threshold, save path, and device.

```bash
paddlex --pipeline instance_segmentation \
        --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_instance_segmentation_004.png \
        --threshold 0.5 \
        --save_path ./output \
        --device gpu:0
```

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

### Download Vehicle Attribute Demo Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md

Use this command to download the demo dataset for vehicle attribute recognition examples to a specified folder. Ensure you have `wget` installed.

```bash
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/vehicle_attribute_examples.tar -P ./dataset
tar -xf ./dataset/vehicle_attribute_examples.tar -C ./dataset/
```

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

### Acquire Example Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/document_scene_information_extraction(layout_detection)_tutorial.en.md

Use these bash commands to download and extract the example 'paperlayout' dataset for layout detection tasks.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/paperlayout.tar -P ./dataset
tar -xf ./dataset/paperlayout.tar -C ./dataset/
```

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

### PHP: Video Classification API Setup

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/video_pipelines/video_classification.en.md

This PHP code snippet initializes the API URL and video path for video classification. It serves as a starting point for making API calls.

```php
<?php

$API_URL = "http://localhost:8080/video-classification"; // Service URL
$video_path = "./demo.mp4";


```

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

### Download Instance Segmentation Dataset Example

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md

Downloads a sample dataset for instance segmentation in LabelMe format. This is a prerequisite for format conversion examples.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/instance_seg_labelme_examples.tar -P ./dataset
tar -xf ./dataset/instance_seg_labelme_examples.tar -C ./dataset/
```

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

### Download Fashion Pedia Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/object_detection_fashion_pedia_tutorial.en.md

Acquire the example dataset for the tutorial. Ensure you are in the correct directory before running these commands.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/det_mini_fashion_pedia_coco.tar -P ./dataset
tar -xf ./dataset/det_mini_fashion_pedia_coco.tar -C ./dataset/
```

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

### Get and Modify OCR Pipeline Configuration

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.md

Steps to retrieve the default OCR pipeline configuration, modify model paths, and then start the service with the custom configuration. This allows for using custom models.

```bash
# 1. 获取 OCR 产线配置文件并保存到 ./OCR.yaml
paddlex --get_pipeline_config OCR --save_path ./OCR.yaml

# 2. 修改 ./OCR.yaml 配置文件
#    将 Pipeline.text_det_model 的值改为 PP-OCRv4_server_det 模型所在路径
#    将 Pipeline.text_rec_model 的值改为 PP-OCRv4_server_rec 模型所在路径

# 3. 启动服务时使用修改后的配置文件
paddlex --serve --pipeline ./OCR.yaml
# 4. 调用服务
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png -O demo.jpg
python fast_test.py
```

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

### Perform VLM Inference with PP-DocBee2-3B

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/vlm_modules/doc_vlm.en.md

Use this snippet to perform inference with the PP-DocBee2-3B model. Ensure you have downloaded the example image and have the PaddleX wheel package installed. The input requires an image path and a query.

```python
from paddlex import create_model
model = create_model('PP-DocBee2-3B')
results = model.predict(
    input={"image": "medal_table.png", "query": "识别这份表格的内容, 以markdown格式输出"},
    batch_size=1
)
for res in results:
    res.print()
    res.save_to_json(f"./output/res.json")
```

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

### PaddleOCR-VL Serving

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/ocr_pipelines/PaddleOCR-VL.en.md

Instructions for installing the serving plugin, running the server, and understanding the command-line options for serving.

```APIDOC
## Serving

### Install Dependencies
```bash
paddlex --install serving
```

### Run the Server
```bash
paddlex --serve --pipeline PaddleOCR-VL-1.6
```

**Configuration Options:**

| Name | Description |
|---|---|
| ` --pipeline` | PaddleX pipeline registration name or pipeline configuration file path. |
| ` --device` | Deployment device for the pipeline. Defaults to GPU if available, otherwise CPU. |
| ` --host` | Hostname or IP address to which the server is bound. Defaults to `0.0.0.0`. |
| ` --port` | Port number on which the server listens. Defaults to `8080`. |
| ` --use_hpip` | If specified, uses high-performance inference. |
| ` --hpi_config` | High-performance inference configuration. |
```

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

### Download Demo Dataset for Video Detection

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/video_modules/video_detection.md

Use this command to download the example dataset for video detection tasks. Ensure you are in the PaddleX project directory before executing.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/video_det_examples.tar -P ./dataset
tar -xf ./dataset/video_det_examples.tar -C ./dataset/
```

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

### Rotated Object Detection Inference

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/rotated_object_detection.md

This snippet demonstrates how to perform inference using a pre-trained rotated object detection model. Ensure you have downloaded the example image and installed the PaddleX wheel package before running.

```python
from paddlex import create_model
model = create_model(model_name="PP-YOLOE-R-L")
output = model.predict(input="rotated_object_detection_001.png", batch_size=1)
for res in output:
    res.print()
    res.save_to_img("./output/")
    res.save_to_json("./output/res.json")
```

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

### Example Usage of Packaging Script

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_deploy/packaging.en.md

Demonstrates how to run the packaging script with and without the --nvidia flag. The --nvidia flag includes CUDA and cuDNN dependencies.

```bash
python package.py --file main.py
# Packages NVIDIA CUDA and cuDNN related dependencies into the same directory as the executable.
python package.py --file main.py --nvidia
```

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

### Table Classification Model Inference

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/ocr_modules/table_classification.en.md

Infers table classification from an image using a pre-trained model. Ensure the PaddleX wheel package is installed and the example image is downloaded locally. The model will be downloaded from HuggingFace by default.

```python
from paddlex import create_model
model = create_model(model_name="PP-LCNet_x1_0_table_cls")
output = model.predict("table_recognition.jpg", batch_size=1)
for res in output:
    res.print(json_format=False)
    res.save_to_json("./output/res.json")
```

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

### Face Feature Extraction Inference

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/face_feature.en.md

This snippet demonstrates how to create a MobileFaceNet model, perform inference on an image to extract face features, and save the results. Ensure you have downloaded the example image and installed the PaddleX package.

```python
from paddlex import create_model

model_name = "MobileFaceNet"

model = create_model(model_name)
output = model.predict("face_recognition_001.jpg", batch_size=1)

for res in output:
    res.print(json_format=False)
    res.save_to_json("./output/res.json")
```

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

### Get and Modify Object Detection Pipeline Configuration

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/deployment_tutorial.md

Steps to retrieve the default object detection pipeline configuration, modify the model path, and start the service with the custom configuration. This is for deploying custom object detection models.

```bash
# 1. 获取 OCR 产线配置文件并保存到 ./object_detection.yaml
paddlex --get_pipeline_config object_detection --save_path ./object_detection.yaml

# 2. 修改 ./object_detection.yaml 配置文件
#    将 Pipeline.model 的值改为 RT-DETR 模型所在路径

# 3. 启动服务时使用修改后的配置文件
paddlex --serve --pipeline ./object_detection.yaml
# 4. 调用服务 | fast_test.py 需要替换为通用目标检测产线使用教程中的 Python 调用示例
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png -O demo.jpg
python fast_test.py
```

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

### C++ Formula Recognition Service Invocation

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md

This C++ example demonstrates how to invoke the formula recognition API using the cpp-httplib and nlohmann/json libraries. It reads an image file, encodes it to base64, sends it to the server, and processes the JSON response. Ensure you have the necessary libraries installed.

```cpp
#include <iostream>
#include <fstream>
#include <vector>
#include <string>
#include "cpp-httplib/httplib.h" // https://github.com/Huiyicc/cpp-httplib
#include "nlohmann/json.hpp" // https://github.com/nlohmann/json
#include "base64.hpp" // https://github.com/tobiaslocker/base64

int main() {
    httplib::Client client("localhost", 8080);

    const std::string filePath = "./demo.jpg";

    std::ifstream file(filePath, std::ios::binary | std::ios::ate);
    if (!file) {
        std::cerr << "Error opening file: " << filePath << std::endl;
        return 1;
    }

    std::streamsize size = file.tellg();
    file.seekg(0, std::ios::beg);
    std::vector<char> buffer(size);
    if (!file.read(buffer.data(), size)) {
        std::cerr << "Error reading file." << std::endl;
        return 1;
    }

    std::string bufferStr(buffer.data(), static_cast<size_t>(size));
    std::string encodedFile = base64::to_base64(bufferStr);

    nlohmann::json jsonObj;
    jsonObj["file"] = encodedFile;
    jsonObj["fileType"] = 1;

    auto response = client.Post("/formula-recognition", jsonObj.dump(), "application/json");

    if (response && response->status == 200) {
        nlohmann::json jsonResponse = nlohmann::json::parse(response->body);
        auto result = jsonResponse["result"];

        if (!result.is_object() || !result["formulaRecResults"].is_array()) {
            std::cerr << "Unexpected response format." << std::endl;
            return 1;
        }

        for (size_t i = 0; i < result["formulaRecResults"].size(); ++i) {
            auto res = result["formulaRecResults"][i];

            if (res.contains("prunedResult")) {
                std::cout << "Recognized formula: " << res["prunedResult"].dump() << std::endl;
            }

            if (res.contains("outputImages") && res["outputImages"].is_object()) {
                for (auto& [imgName, imgData] : res["outputImages"].items()) {
                    std::string outputPath = imgName + "_" + std::to_string(i) + ".jpg";
                    std::string decodedImage = base64::from_base64(imgData.get<std::string>());

```

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

### Face Detection Inference with PaddleX

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/face_detection.en.md

Perform face detection inference on an image using a pre-trained model. This snippet demonstrates model creation, prediction, and saving results to an image and JSON file. Ensure you have downloaded the example image and installed the PaddleX wheel package.

```python
from paddlex import create_model

model_name = "PicoDet_LCNet_x2_5_face"

model = create_model(model_name)
output = model.predict("face_detection.png", batch_size=1)

for res in output:
    res.print(json_format=False)
    res.save_to_img("./output/")
    res.save_to_json("./output/res.json")
```

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

### Download Demo Dataset for Layout Analysis

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/ocr_modules/layout_analysis.en.md

Use these commands to download the demo dataset for layout analysis to a specified folder. Ensure you are in the correct directory before executing.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/doclayoutv3_examples.tar -P ./dataset
tar -xf ./dataset/doclayoutv3_examples.tar -C ./dataset/
```

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

### Download Demo Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/small_object_detection.md

Use this command to download the demo dataset for small object detection examples. Ensure you are in the correct directory before executing.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/small_det_examples.tar -P ./dataset
tar -xf ./dataset/small_det_examples.tar -C ./dataset/
```

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

### Run Layout Parsing Pipeline via Command Line

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

Execute the layout parsing pipeline using the command line. Ensure PaddleX is installed and specify input, output paths, and model configurations. This example uses a sample image and disables document orientation and unwarping.

```bash
paddlex --pipeline layout_parsing \
        --input layout_parsing_demo.png \
        --use_doc_orientation_classify False \
        --use_doc_unwarping False \
        --use_textline_orientation False \
        --save_path ./output \
        --device gpu:0
```

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

### Table Cell Detection Inference

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/ocr_modules/table_cells_detection.en.md

This snippet demonstrates how to load a pre-trained table cell detection model and perform inference on an image. It shows how to print the results, save them to an image, and save them to a JSON file. Ensure you have the PaddleX wheel package installed and the example image downloaded.

```python
from paddlex import create_model
model = create_model(model_name="RT-DETR-L_wired_table_cell_det")
output = model.predict("table_recognition.jpg",  threshold=0.3, batch_size=1)
for res in output:
    res.print(json_format=False)
    res.save_to_img("./output/")
    res.save_to_json("./output/res.json")
```

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

### Create and Run Instance Segmentation Pipeline in Python

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md

Demonstrates how to create an instance segmentation pipeline using a custom configuration file and perform predictions on an image. It shows how to iterate through results, print them, and save them to files.

```python
from paddlex import create_pipeline

pipeline = create_pipeline(pipeline="./my_path/instance_segmentation.yaml")

output = pipeline.predict(
    input="./general_instance_segmentation_004.png",
    threshold=0.5,
)
for res in output:
    res.print()
    res.save_to_img("./output/")
    res.save_to_json("./output/")

```

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

### Verify PaddlePaddle Installation

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/installation/paddlepaddle_install.md

Run this command after installation to verify if PaddlePaddle is installed successfully and to check the installed version.

```bash
python -c "import paddle; print(paddle.__version__)"
```

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

### Download Demo Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/module_usage/tutorials/cv_modules/image_feature.en.md

Use this command to download the example dataset for the Image Feature module to a specified directory.

```bash
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Inshop_examples.tar -P ./dataset
tar -xf ./dataset/Inshop_examples.tar -C ./dataset/
```

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

### Download Example Dataset

Source: https://github.com/paddlepaddle/paddlex/blob/release/3.7/docs/practical_tutorials/face_recognition_tutorial.md

Use this command to download the cartoon face detection dataset for the tutorial. Ensure you are in the PaddleX project directory.

```bash
cd /path/to/paddlex
wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/cartoonface_coco_examples.tar -P ./dataset
tar -xf ./dataset/cartoonface_coco_examples.tar -C ./dataset/
```