百度PaddlePaddle抠图

环境准备

　　python 版本需要是 3.6 至 3.10。pip 版本需要是 20.2.2 或更高。本地安装的是 python 3.6，pip 版本升级到了 21.3.1。

python --version
>>Python 3.6.4

pip3 --version
>>pip 20.1 from d:\program files\python36\lib\site-packages\pip (python 3.6)

pip install -U pip
>>Successfully installed pip-21.3.1

安装PaddlePaddle

python -m pip install paddlepaddle==2.4.1 -i https://pypi.tuna.tsinghua.edu.cn/simple

安装 PaddleHub

pip install --upgrade paddlehub -i https://pypi.tuna.tsinghua.edu.cn/simple

验证

python
>>> import paddle

>>> paddle.utils.run_check()
Running verify PaddlePaddle program ...
PaddlePaddle works well on 2 CPUs.
PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.
>>> exit()

示例代码

import os
import paddlehub as hub

humanseg = hub.Module(name='deeplabv3p_xception65_humanseg')

path = 'G:/Library/Desktop/images/'

files = os.listdir(path)
print(files)

imgs = []

for img in files:
    imgs.append(path + img)

results = humanseg.segmentation(data={'image':imgs},visualization=True,output_dir=path+'result')

　　执行脚本，结果报错：ModuleNotFoundError: No module named 'scipy'。安装 scipy 之后再次执行，报出错误：SyntaxError: future feature annotations is not defined。本地的 python 环境保持了好几年了，看来飞桨官网说的也过时了啊，升级到 python 3.10，需要重新安装 PaddleHub 和 PaddlePaddle。然后再次执行脚本。

原图：163KB

处理后：1.76MB