https://paddlepaddle.github.io/PaddleX/main/pipeline_usage/tutorials/cv_pipelines/face_recognition.html#222-python

from paddlex import create_pipeline

pipeline = create_pipeline(pipeline="face_recognition")

pipeline.build_index(data_root="face_demo_gallery", index_dir="face_gallery_index")

output = pipeline.predict("friends1.jpg", index_dir="face_gallery_index")
for res in output:
res.print()
res.save_to_img("./output/")

控制台打印：
Using official model (MobileFaceNet), the model files will be be automatically downloaded and saved in C:\Users\PC.paddlex\official_models.
Traceback (most recent call last):
File "D:\code\PaddleX\myUtils\face_test.py", line 5, in
pipeline.build_index(data_root="face_demo_gallery", index_dir="face_gallery_index")
TypeError: ShiTuV2Pipeline.build_index() missing 2 required positional arguments: 'gallery_imgs' and 'gallery_label'