sml2h3/ddddocr

带带弟弟 通用验证码识别OCR pypi版

ddddocr's Issues

英文大小写识别开启问题✌️

请问框架如何开启英文识别大小写呢

可以支持区分大小写吗？

如题。谢谢！

异常报错

这是个啥情况呢

对于已知类型和字符个数的验证码，能否提高识别率

比如我知道这个验证码是四位英文字符和数字组合，能不能限定范围，提高识别率呢？

如何部署GPU版本

@sml2h3 您好，请问您部署过GPU版本吗？我将模型设置如下
self.ocr = ddddocr.DdddOcr(use_gpu=True, old=True)
在推理时会有如下报错
TypeError: load_model(): incompatible function arguments. The following argument types are supported:
1. (self: onnxruntime.capi.onnxruntime_pybind11_state.InferenceSession, arg0: List[str]) -> None
Invoked with: <onnxruntime.capi.onnxruntime_pybind11_state.InferenceSession object at 0x7f3754e7dce0>, [('CUDAExecutionProvider', {'device_id': 0, 'arena_extend_strategy': 'kNextPowerOfTwo', 'cuda_mem_limit': 1073741824, 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': True})]
您有什么解决办法吗？ 感谢！

请问我用pyinstaller修改了spec把common.onnx包含在data后-F封装，exe还是闪退是什么情况呢

之前是显示 no such file：common.onnx，后来我修改了spec，把common.onnx加入了，可以在我自己的电脑执行exe。
但是到没有安装python的电脑环境下，就出现闪退了。（我的py代码中有selenium的部分，我还特意把webdriver.exe和生成的exe放到了同一目录，依旧闪退）

大佬，为什么我运行不了，总是报错

Traceback (most recent call last):
File "D:/python/201.py", line 3, in
ocr = ddddocr.DdddOcr()
File "D:\python\lib\site-packages\ddddocr_init_.py", line 29, in init
self.__ort_session = onnxruntime.InferenceSession(self.__graph_path, providers=self.__providers)
File "D:\python\lib\site-packages\onnxruntime\capi\session.py", line 195, in init
self._create_inference_session(providers, provider_options)
File "D:\python\lib\site-packages\onnxruntime\capi\session.py", line 200, in _create_inference_session
sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from D:\python\lib\site-packages\ddddocr\common.onnx failed:Fatal error: DynamicQuantizeLSTM is not a registered function/op

使用时报错

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x00000219E6A236D0>

识别效果不好的图收集

在这里可以把你觉得识别效果不好的图片发在这里。
希望贴3张以上原图，可以包含原图链接。

除了卧槽/牛逼，还想问问以后会不会支持旋转验证码

比方百度旋转验证码这种

这个如何识别算式型验证码

试了几张图，无法识别符号，只能识别出数字

readme过时了吗，1.3.0不支持old参数

Traceback (most recent call last):
  File "yzm.py", line 5, in <module>
    ocr = ddddocr.DdddOcr(old=True)
TypeError: __init__() got an unexpected keyword argument 'old'

这种验证码百分百失败

这种验证码百分百失败，都是返回单字母 d

onnxruntime 下载不了

显示 ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'onnxruntime'

安装报错？

使用命令 pip install ddddocr 安装时报错：

ERROR: Could not find a version that satisfies the requirement onnxruntime (from ddddocr) (from versions: none)
ERROR: No matching distribution found for onnxruntime

怎么回事？

Python版本：3.10.0

异常报错-找不到指定的模块

大佬大佬，这种情况需要如何处理呢

在容器中无法运行

Traceback (most recent call last):
File "hello.py", line 8, in
import cv2
File "/usr/local/lib/python3.8/site-packages/cv2/init.py", line 8, in
from .cv2 import *

ImportError: libGL.so.1: cannot open shared object file: No such file or directory
下载过后错误又变为
libGL.so.0

如何识别多行内容

目前只能识别一行内容，如果有多行内容，则无输出

模型训练😁

首先感谢带带弟弟的开源精神，我是在校大学生，对这方面比较感兴趣，请问如何训练模型，是否开源呢？

我有一个闪动的gif验证码，4个字符，可以识别出后3个，第1个被忽略了。

提供三个样本：

代码：
`import ddddocr

ocr = ddddocr.DdddOcr(old=True)
with open('3.gif', 'rb') as f:
img_bytes = f.read()
res = ocr.classification(img_bytes)

print(res)`

获取不到验证码，这种问题是什么原因啊？

根据提示选文字按顺序选取的功能不支持吗?

如题

Fatal error: DynamicQuantizeLSTM is not a registered function/op

Fatal error: DynamicQuantizeLSTM is not a registered function/op

有ddddocr的训练集吗

想自己尝试一下训练ddddocr使用的模型，但是自己的数据集一直有问题。不够全面，而且准确性一直是0

pyinstaller 打包成功后运行报错

2022-02-08 16:47:20,950 - 日志 - ERROR - [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed:Load model C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed. File doesn't exist
2022-02-08 16:47:21,474 - 日志 - ERROR - 方国民失败[ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed:Load model C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed. File doesn't exist
2022-02-08 16:47:21,853 - 日志 - ERROR - 田东礼失败[ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed:Load model C:\Users\ADMINI1\AppData\Local\Temp_MEI13522\ddddocr\common_old.onnx failed. File doesn't exist

不能用呀

AttributeError: partially initialized module 'ddddocr' has no attribute 'DdddOcr' (most likely due to a circular import)

图片的base64字符串需要取头部吗

传入的base64字符串有什么规则要求吗

解析每次都弹警告信息

2021-07-30 15:45:48.3226553 [W:onnxruntime:, execution_frame.cc:721 onnxruntime::ExecutionFrame::VerifyOutputSizes] Expected shape from model of {1,19} does not match actual shape of {1,20} for output output

【报错】ImportError: DLL load failed: 找不到指定的模块。

import ddddocr
环境：Python 3.7.3，win10

Traceback (most recent call last):
File "", line 1, in
File "D:\python3\lib\site-packages\ddddocr_init_.py", line 9, in
import onnxruntime
File "D:\python3\lib\site-packages\onnxruntime_init_.py", line 35, in
raise import_capi_exception
File "D:\python3\lib\site-packages\onnxruntime_init_.py", line 23, in
from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, set_seed,
File "D:\python3\lib\site-packages\onnxruntime\capi_pybind_state.py", line 32, in
from .onnxruntime_pybind11_state import * # noqa
ImportError: DLL load failed: 找不到指定的模块。

大佬. 这张图转成base64 ocr返回是空的 det可以监测到位置, 能否det加上是哪个文字呢

容器中报错（即使更换为opencv-python-headless也无法解决）

若使用opencv-python则“libGL.so.1: cannot open shared object file: No such file or directory”
opencv-python-headless则
”Traceback (most recent call last):
File "main.py", line 1, in
import ddddocr
File "/home/runner/ocr/venv/lib/python3.8/site-packages/ddddocr/init.py", line 12, in
import cv2
File "/home/runner/ocr/venv/lib/python3.8/site-packages/cv2/init.py", line 190, in
bootstrap()
File "/home/runner/ocr/venv/lib/python3.8/site-packages/cv2/init.py", line 120, in bootstrap
load_first_config(['config.py'], True)
File "/home/runner/ocr/venv/lib/python3.8/site-packages/cv2/init.py", line 118, in load_first_config
raise ImportError('OpenCV loader: missing configuration file: {}. Check OpenCV installation.'.format(fnames))
ImportError: OpenCV loader: missing configuration file: ['config.py']. Check OpenCV installation.“

ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none)

pip无法安装ddddocr，换了好几个源，都提示这个
ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none)
ERROR: No matching distribution found for onnxruntime

有个不太成熟的小想法

怎么训练通用的模型

Win10 20H2 + Python3.9.5无法安装

pip install ddddocr
Collecting ddddocr
Using cached ddddocr-1.0.6-py3-none-any.whl (6.9 MB)
Using cached ddddocr-1.0.5-py3-none-any.whl (3.3 MB)
Collecting torchvision
Using cached torchvision-0.2.2.post3-py2.py3-none-any.whl (64 kB)
Collecting ddddocr
Using cached ddddocr-1.0.4.tar.gz (3.3 MB)
Requirement already satisfied: numpy in e:\program files\python\python39-32\lib\site-packages (from ddddocr) (1.20.3)
ERROR: Cannot install ddddocr==1.0.4, ddddocr==1.0.5 and ddddocr==1.0.6 because these package versions have conflicting dependencies.

The conflict is caused by:
ddddocr 1.0.6 depends on onnxruntime
ddddocr 1.0.5 depends on onnxruntime
ddddocr 1.0.4 depends on torchvision==0.9.1

To fix this you could try to:

1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/user_guide/#fixing-conflicting-dependencies

M1 Mac安装报错

如题。M1 Mac安装报错。请问是系统问题吗？

ERROR: Cannot install ddddocr==1.0.6 and ddddocr==1.1.0 because these package versions have conflicting dependencies.

The conflict is caused by:
    ddddocr 1.1.0 depends on onnxruntime
    ddddocr 1.0.6 depends on onnxruntime

To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/user_guide/#fixing-conflicting-dependencies
monkey@benboerba ~ % ~/Documents/python_env/wuyou/bin/pip3 install onnxruntime
ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none)
ERROR: No matching distribution found for onnxruntime

opencv-python的依赖可否换为opencv-python-headless

此处是opencv-python-headless的介绍

These packages are smaller than the two other packages above because they do not contain any GUI functionality (not compiled with Qt / other GUI components). This means that the packages avoid a heavy dependency chain to X11 libraries and you will have for example smaller Docker images as a result. You should always use these packages if you do not use cv2.imshow et al. or you are using some other package (such as PyQt) than OpenCV to create your GUI.
Option 3 - Headless main modules package: pip install opencv-python-headless
Option 4 - Headless full package (contains both main modules and contrib/extra modules): pip install opencv-contrib-python-headless (check contrib/extra modules listing from OpenCV documentation)

验证码大小写解决了么

请教一下关于提高正确识别率的问题

在直接识别的情况下会出现挺高的错误（见下面图片），想请教下在已知验证码图片有以下规律的情况下想提高识别率，大佬能否提供一点意见。。

1、全都是单一色调
2、全部都是五个字母组成
3、干扰因素只有一条从左到右的线条

Error

pip3 install ddddocr Collecting ddddocr Using cached ddddocr-1.0.6-py3-none-any.whl (6.9 MB) Collecting Pillow Using cached Pillow-9.0.1-cp310-cp310-macosx_10_10_universal2.whl (3.3 MB) ERROR: Could not find a version that satisfies the requirement onnxruntime (from ddddocr) (from versions: none) ERROR: No matching distribution found for onnxruntime

Python 3.10.2

不是M1
macOS BigSur 11.6.3 (20G415)
MacBook Pro (Retina, 13-inch, Late 2013) Intel
也不支持？

识别不了验证码里的小数点

识别不了验证码里的小数点。。。

请问我将程序封装后运行，每次都报这种错误是什么原因啊？

[ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from C:\Users\ADMINI~1\AppData\Local

\Temp\2_MEI30202\ddddocr\common.onnx failed:Load model C:\Users\ADMINI~1\AppData\Local

\Temp\2_MEI30202\ddddocr\common.onnx failed. File doesn't exist

麻烦帮忙看下，十分感谢。

无法安装

(base) F:>pip install ddddocr==1.0.6
ERROR: Could not find a version that satisfies the requirement ddddocr==1.0.6 (from versions: none)
ERROR: No matching distribution found for ddddocr==1.0.6

File "D:\codetools\anaconda3\lib\site-packages\onnxruntime\capi\_pybind_state.py", line 32, in <module> from .onnxruntime_pybind11_state import * # noqa ImportError: DLL load failed while importing onnxruntime_pybind11_state: 找不到指定的模块。

import ddddocr 跳这个错误怎么解决

询问下大概什么时候能支持macos m系列处理器?或者有没有自己编译onnxruntime的文档?谢谢

感谢!~

还是有onnxruntime exception

2021-11-17 01:56:58.2197926 [W:onnxruntime:, execution_frame.cc:770 onnxruntime::ExecutionFrame::VerifyOutputSizes] Expected shape from model of {1,19} does not match actual shape of {1,17} for output output

谢谢大佬的识别包, 发现一个问题..
下载的最新版,也试过update, 运行的时候还有这个错误提示.

MacOS无法安装

系统版本：11.4 (20F71)
设备版本：MacBook Air (M1, 2020)
pip安装提示没有版本可用
ERROR: Cannot install ddddocr==1.0.4, ddddocr==1.0.5 and ddddocr==1.0.6 because these package versions have conflicting dependencies.

异常报错'ddddocr' has no attribute 'DdddOcr'

AttributeError: partially initialized module 'ddddocr' has no attribute 'DdddOcr' (most likely due to a circular import)

import 无法导入包，似需要依赖配置文件

额，字典搞成txt，加载单独文件是不是比放代码里更优雅

Bump PyPI version to works with Python >= 3.8

python3.9报错无法使用

提示AttributeError: partially initialized module 'ddddocr' has no attribute 'DdddOcr' (most likely due to a circular import)