python 百度ocr安装_window10 python 3.6.8 本地 OCR 模块 muggle_ocr 安装实践

其实最主要还是 muggle-ocr-1.0.tar.gz (6.37M)和 tensorflow-2.2.0-cp36-cp36m-win_amd64.whl (437M) 这两个依赖包的下载,下载预期时间超长,或者容易出现 timeout。

百度云盘下载

安装技巧

pip 安装过程中,会出现多次出现 timeout,此时可以把下载文件的链接复制下来,用迅雷等工具直接下载,然后直接安装文件。中途碰到依赖包下载失败的情况,也可以采取换源方式下载安装。

demo 运行日志

2020-06-03 16:21:57.226907: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found

2020-06-03 16:21:57.233320: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.

2020-06-03 16:22:02.692999: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2

2020-06-03 16:22:02.706948: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1fa8dd3be30 initialized for platform Host (this does not guarantee that XLA will be used). Devices:

2020-06-03 16:22:02.712914: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version

2020-06-03 16:22:02.724346: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found

2020-06-03 16:22:02.729600: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)

2020-06-03 16:22:02.746110: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: DESKTOP-9K42C1Q

2020-06-03 16:22:02.752040: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: DESKTOP-9K42C1Q

MuggleOCR Session [ocr] Loaded.

曹文轩教授作序推荐 0.016988515853881836

曹文轩教授作序推荐 0.01699233055114746

曹文轩教授作序推荐 0.01898980140686035

曹文轩教授作序推荐 0.017995595932006836

曹文轩教授作序推荐 0.017983675003051758

MuggleOCR Session [captcha] Loaded.

ceey 0.019988536834716797

ceey 0.01898932456970215

ceey 0.019996166229248047

ceey 0.017989397048950195

ceey 0.0209963321685791

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值