# GPU安装
python3 -m pip install paddlepaddle-gpu==2.1.1 -i https://mirror.baidu.com/pypi/simple

# CPU安装
 python3 -m pip install paddlepaddle==2.1.1 -i https://mirror.baidu.com/pypi/simple

=2.2"">

pip3 install -U https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
pip install "paddleocr>=2.2"

pip3 install -r requirements.txt

FocusAX
    - paperparse
        - ppyolov2_r50vd_dcn_365e_publaynet
            - inference.pdiparams
            - inference.pdiparams.info
            - inference.pdmodel
        - ...
    - downloader
        - ...
    - utils
        - ...
    - configs.py
    - focus_daily.py
    - focus_search.py
    - README.py
    - ...

# =============== 网络代理 ================
# proxy = None # 不使用代理
proxy = {"http": "socks5://127.0.0.1:8080", "https": "socks5://127.0.0.1:8080"}
# =============== 保存文件根目录 ================
root_path = "./arxiv"
# =============== DNN模型推理配置信息 ================
threshold = 0.5
enable_mkldnn = True
enforce_cpu = True
thread_num = 4

if __name__ == '__main__':
    key_words = ['GAN'] # 要包含的关键词
    subject_words = ['ML', 'CV', 'AI']  # 要包含的类别
    start_parse(key_words, subject_words, needPDF=True, needZip=False)

start_parse('Keyword')