├── .gitignore ├── LICENSE ├── README.md ├── captcha_cnn_model.py ├── captcha_gen.py ├── captcha_predict.py ├── captcha_setting.py ├── captcha_test.py ├── captcha_train.py ├── dataset ├── predict │ ├── 2BVC_1539936857.png │ ├── 5X09_1539936857.png │ ├── JFA6_1539936857.png │ ├── KAWJ_1539936857.png │ └── X4E9_1539936857.png ├── test │ ├── 1BWB_1539937370.png │ ├── 1G4J_1539937370.png │ └── 2PUI_1539937370.png └── train │ ├── 11IL_1539937370.png │ ├── 1BWB_1539937370.png │ ├── 1G4J_1539937370.png │ ├── 2PUI_1539937370.png │ ├── 2TFY_1539937370.png │ ├── 2ZWW_1539937370.png │ ├── 46AL_1539937370.png │ ├── 4MEM_1539937370.png │ ├── 55IC_1539937370.png │ ├── A41S_1539937370.png │ ├── AVQK_1539937370.png │ ├── B647_1539937370.png │ ├── DRF0_1539937370.png │ ├── F3SR_1539937370.png │ ├── F4I1_1539937370.png │ ├── GQT4_1539937370.png │ ├── HQM1_1539937370.png │ ├── HWD5_1539937370.png │ ├── IDQY_1539937370.png │ ├── MFVG_1539937370.png │ ├── MLYM_1539937370.png │ ├── OIW9_1539937370.png │ ├── P9QN_1539937370.png │ ├── PY55_1539937370.png │ ├── RB3A_1539937370.png │ ├── S50Z_1539937370.png │ ├── U206_1539937370.png │ ├── UV27_1539937370.png │ ├── XK7E_1539937370.png │ └── XY0K_1539937370.png ├── docs ├── number.png └── number2.png ├── my_dataset.py └── one_hot_encoding.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 56 | 57 | # Flask stuff: 58 | instance/ 59 | .webassets-cache 60 | 61 | # Scrapy stuff: 62 | .scrapy 63 | 64 | # Sphinx documentation 65 | docs/_build/ 66 | 67 | # PyBuilder 68 | target/ 69 | 70 | # Jupyter Notebook 71 | .ipynb_checkpoints 72 | 73 | # pyenv 74 | .python-version 75 | 76 | # celery beat schedule file 77 | celerybeat-schedule 78 | 79 | # SageMath parsed files 80 | *.sage.py 81 | 82 | # dotenv 83 | .env 84 | 85 | # virtualenv 86 | .venv 87 | venv/ 88 | ENV/ 89 | 90 | # Spyder project settings 91 | .spyderproject 92 | .spyproject 93 | 94 | # Rope project settings 95 | .ropeproject 96 | 97 | # mkdocs documentation 98 | /site 99 | 100 | # mypy 101 | .mypy_cache/ 102 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 深度学习识别验证码 2 | ========= 3 | 4 | 本项目致力于使用神经网络来识别各种验证码。 5 | 6 | 特性 7 | === 8 | - __端到端，不需要做更多的图片预处理（比如图片字符切割、图片尺寸归一化、图片字符标记、字符图片特征提取）__ 9 | - __验证码包括数字、大写字母、小写__ 10 | - __采用自己生成的验证码来作为神经网络的训练集合、测试集合、预测集合__ 11 | - __纯四位数字，验证码识别率高达 99.9999 %__ 12 | - __四位数字 + 大写字符，验证码识别率约 96 %__ 13 | - __深度学习框架pytorch + 验证码生成器ImageCaptcha__ 14 | 15 | 16 | 原理 17 | === 18 | 19 | - __训练集合生成__ 20 | 21 | 使用常用的 Python 验证码生成库 ImageCaptcha，生成 10w 个验证码，并且都自动标记好; 22 | 如果需要识别其他的验证码也同样的道理，寻找对应的验证码生成算法自动生成已经标记好的训练集合或者手动对标记，需要上万级别的数量，纯手工需要一定的时间，再或者可以借助一些网络的打码平台进行标记 23 | 24 | - __训练卷积神经网络__ 25 | 构建一个多层的卷积网络，进行多标签分类模型的训练 26 | 标记的每个字符都做 one-hot 编码 27 | 批量输入图片集合和标记数据，大概15个Epoch后，准确率已经达到 96% 以上 28 | 29 | 30 | 验证码识别率展示 31 | ======== 32 | ![](https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/master/docs/number.png) 33 | ![](https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/master/docs/number2.png) 34 | 35 | 36 | 快速开始 37 | ==== 38 | - __步骤一：10分钟环境安装__ 39 | 40 | Python2.7+ 、ImageCaptcha库(pip install captcha)、 Pytorch(参考官网http://pytorch.org) 41 | 42 | 43 | - __步骤二：生成验证码__ 44 | ```bash 45 | python captcha_gen.py 46 | ``` 47 | 执行以上命令，会在目录 dataset/train/ 下生成多张验证码图片，图片已经标注好，数量可以是 1w、5w、10w，通过 captcha-gen.py 内的 count 参数设定 48 | 49 | - __步骤三：训练模型__ 50 | ```bash 51 | python captcha_train.py 52 | ``` 53 | 使用步骤一生成的验证码图集合用CNN模型（在 catcha_cnn_model 中定义）进行训练，训练完成会生成文件 model.pkl 54 | 55 | - __步骤四：测试模型__ 56 | ```bash 57 | python captcha_test.py 58 | ``` 59 | 可以在控制台，看到模型的准确率（如 95%） ，如果准确率较低，回到步骤一，生成更多的图片集合再次训练 60 | 61 | - __步骤五：使用模型做预测__ 62 | ```bash 63 | python captcha_predict.py 64 | ``` 65 | 可以在控制台，看到预测输出的结果 66 | 67 | 贡献 68 | === 69 | 我们期待你的 pull requests ! 70 | 71 | 作者 72 | === 73 | * __Dee Qiu__ 74 | 75 | 其它 76 | === 77 | * __Github项目交流QQ群__ 570997546 78 | 79 | 80 | 声明 81 | === 82 | 本项目仅用于交流学习 -------------------------------------------------------------------------------- /captcha_cnn_model.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import torch.nn as nn 3 | import captcha_setting 4 | 5 | # CNN Model (2 conv layer) 6 | class CNN(nn.Module): 7 | def __init__(self): 8 | super(CNN, self).__init__() 9 | self.layer1 = nn.Sequential( 10 | nn.Conv2d(1, 32, kernel_size=3, padding=1), 11 | nn.BatchNorm2d(32), 12 | nn.Dropout(0.5), # drop 50% of the neuron 13 | nn.ReLU(), 14 | nn.MaxPool2d(2)) 15 | self.layer2 = nn.Sequential( 16 | nn.Conv2d(32, 64, kernel_size=3, padding=1), 17 | nn.BatchNorm2d(64), 18 | nn.Dropout(0.5), # drop 50% of the neuron 19 | nn.ReLU(), 20 | nn.MaxPool2d(2)) 21 | self.layer3 = nn.Sequential( 22 | nn.Conv2d(64, 64, kernel_size=3, padding=1), 23 | nn.BatchNorm2d(64), 24 | nn.Dropout(0.5), # drop 50% of the neuron 25 | nn.ReLU(), 26 | nn.MaxPool2d(2)) 27 | self.fc = nn.Sequential( 28 | nn.Linear((captcha_setting.IMAGE_WIDTH//8)*(captcha_setting.IMAGE_HEIGHT//8)*64, 1024), 29 | nn.Dropout(0.5), # drop 50% of the neuron 30 | nn.ReLU()) 31 | self.rfc = nn.Sequential( 32 | nn.Linear(1024, captcha_setting.MAX_CAPTCHA*captcha_setting.ALL_CHAR_SET_LEN), 33 | ) 34 | 35 | def forward(self, x): 36 | out = self.layer1(x) 37 | out = self.layer2(out) 38 | out = self.layer3(out) 39 | out = out.view(out.size(0), -1) 40 | out = self.fc(out) 41 | out = self.rfc(out) 42 | return out 43 | 44 | -------------------------------------------------------------------------------- /captcha_gen.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | from captcha.image import ImageCaptcha # pip install captcha 3 | from PIL import Image 4 | import random 5 | import time 6 | import captcha_setting 7 | import os 8 | 9 | def random_captcha(): 10 | captcha_text = [] 11 | for i in range(captcha_setting.MAX_CAPTCHA): 12 | c = random.choice(captcha_setting.ALL_CHAR_SET) 13 | captcha_text.append(c) 14 | return ''.join(captcha_text) 15 | 16 | # 生成字符对应的验证码 17 | def gen_captcha_text_and_image(): 18 | image = ImageCaptcha() 19 | captcha_text = random_captcha() 20 | captcha_image = Image.open(image.generate(captcha_text)) 21 | return captcha_text, captcha_image 22 | 23 | if __name__ == '__main__': 24 | count = 30 25 | path = captcha_setting.TRAIN_DATASET_PATH #通过改变此处目录，以生成 训练、测试和预测用的验证码集 26 | if not os.path.exists(path): 27 | os.makedirs(path) 28 | for i in range(count): 29 | now = str(int(time.time())) 30 | text, image = gen_captcha_text_and_image() 31 | filename = text+'_'+now+'.png' 32 | image.save(path + os.path.sep + filename) 33 | print('saved %d : %s' % (i+1,filename)) 34 | 35 | -------------------------------------------------------------------------------- /captcha_predict.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import numpy as np 3 | import torch 4 | from torch.autograd import Variable 5 | #from visdom import Visdom # pip install Visdom 6 | import captcha_setting 7 | import my_dataset 8 | from captcha_cnn_model import CNN 9 | 10 | def main(): 11 | cnn = CNN() 12 | cnn.eval() 13 | cnn.load_state_dict(torch.load('model.pkl')) 14 | print("load cnn net.") 15 | 16 | predict_dataloader = my_dataset.get_predict_data_loader() 17 | 18 | #vis = Visdom() 19 | for i, (images, labels) in enumerate(predict_dataloader): 20 | image = images 21 | vimage = Variable(image) 22 | predict_label = cnn(vimage) 23 | 24 | c0 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 0:captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 25 | c1 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, captcha_setting.ALL_CHAR_SET_LEN:2 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 26 | c2 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 2 * captcha_setting.ALL_CHAR_SET_LEN:3 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 27 | c3 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 3 * captcha_setting.ALL_CHAR_SET_LEN:4 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 28 | 29 | c = '%s%s%s%s' % (c0, c1, c2, c3) 30 | print(c) 31 | #vis.images(image, opts=dict(caption=c)) 32 | 33 | if __name__ == '__main__': 34 | main() 35 | 36 | 37 | -------------------------------------------------------------------------------- /captcha_setting.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import os 3 | # 验证码中的字符 4 | # string.digits + string.ascii_uppercase 5 | NUMBER = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'] 6 | ALPHABET = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'] 7 | 8 | ALL_CHAR_SET = NUMBER + ALPHABET 9 | ALL_CHAR_SET_LEN = len(ALL_CHAR_SET) 10 | MAX_CAPTCHA = 4 11 | 12 | # 图像大小 13 | IMAGE_HEIGHT = 60 14 | IMAGE_WIDTH = 160 15 | 16 | TRAIN_DATASET_PATH = 'dataset' + os.path.sep + 'train' 17 | TEST_DATASET_PATH = 'dataset' + os.path.sep + 'test' 18 | PREDICT_DATASET_PATH = 'dataset' + os.path.sep + 'predict' -------------------------------------------------------------------------------- /captcha_test.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import numpy as np 3 | import torch 4 | from torch.autograd import Variable 5 | import captcha_setting 6 | import my_dataset 7 | from captcha_cnn_model import CNN 8 | import one_hot_encoding 9 | 10 | def main(): 11 | cnn = CNN() 12 | cnn.eval() 13 | cnn.load_state_dict(torch.load('model.pkl')) 14 | print("load cnn net.") 15 | 16 | test_dataloader = my_dataset.get_test_data_loader() 17 | 18 | correct = 0 19 | total = 0 20 | for i, (images, labels) in enumerate(test_dataloader): 21 | image = images 22 | vimage = Variable(image) 23 | predict_label = cnn(vimage) 24 | 25 | c0 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 0:captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 26 | c1 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, captcha_setting.ALL_CHAR_SET_LEN:2 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 27 | c2 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 2 * captcha_setting.ALL_CHAR_SET_LEN:3 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 28 | c3 = captcha_setting.ALL_CHAR_SET[np.argmax(predict_label[0, 3 * captcha_setting.ALL_CHAR_SET_LEN:4 * captcha_setting.ALL_CHAR_SET_LEN].data.numpy())] 29 | predict_label = '%s%s%s%s' % (c0, c1, c2, c3) 30 | true_label = one_hot_encoding.decode(labels.numpy()[0]) 31 | total += labels.size(0) 32 | if(predict_label == true_label): 33 | correct += 1 34 | if(total%200==0): 35 | print('Test Accuracy of the model on the %d test images: %f %%' % (total, 100 * correct / total)) 36 | print('Test Accuracy of the model on the %d test images: %f %%' % (total, 100 * correct / total)) 37 | 38 | if __name__ == '__main__': 39 | main() 40 | 41 | 42 | -------------------------------------------------------------------------------- /captcha_train.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import torch 3 | import torch.nn as nn 4 | from torch.autograd import Variable 5 | import my_dataset 6 | from captcha_cnn_model import CNN 7 | 8 | # Hyper Parameters 9 | num_epochs = 30 10 | batch_size = 100 11 | learning_rate = 0.001 12 | 13 | def main(): 14 | cnn = CNN() 15 | cnn.train() 16 | print('init net') 17 | criterion = nn.MultiLabelSoftMarginLoss() 18 | optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate) 19 | 20 | # Train the Model 21 | train_dataloader = my_dataset.get_train_data_loader() 22 | for epoch in range(num_epochs): 23 | for i, (images, labels) in enumerate(train_dataloader): 24 | images = Variable(images) 25 | labels = Variable(labels.float()) 26 | predict_labels = cnn(images) 27 | # print(predict_labels.type) 28 | # print(labels.type) 29 | loss = criterion(predict_labels, labels) 30 | optimizer.zero_grad() 31 | loss.backward() 32 | optimizer.step() 33 | if (i+1) % 10 == 0: 34 | print("epoch:", epoch, "step:", i, "loss:", loss.item()) 35 | if (i+1) % 100 == 0: 36 | torch.save(cnn.state_dict(), "./model.pkl") #current is model.pkl 37 | print("save model") 38 | print("epoch:", epoch, "step:", i, "loss:", loss.item()) 39 | torch.save(cnn.state_dict(), "./model.pkl") #current is model.pkl 40 | print("save last model") 41 | 42 | if __name__ == '__main__': 43 | main() 44 | 45 | 46 | -------------------------------------------------------------------------------- /dataset/predict/2BVC_1539936857.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/predict/2BVC_1539936857.png -------------------------------------------------------------------------------- /dataset/predict/5X09_1539936857.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/predict/5X09_1539936857.png -------------------------------------------------------------------------------- /dataset/predict/JFA6_1539936857.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/predict/JFA6_1539936857.png -------------------------------------------------------------------------------- /dataset/predict/KAWJ_1539936857.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/predict/KAWJ_1539936857.png -------------------------------------------------------------------------------- /dataset/predict/X4E9_1539936857.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/predict/X4E9_1539936857.png -------------------------------------------------------------------------------- /dataset/test/1BWB_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/test/1BWB_1539937370.png -------------------------------------------------------------------------------- /dataset/test/1G4J_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/test/1G4J_1539937370.png -------------------------------------------------------------------------------- /dataset/test/2PUI_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/test/2PUI_1539937370.png -------------------------------------------------------------------------------- /dataset/train/11IL_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/11IL_1539937370.png -------------------------------------------------------------------------------- /dataset/train/1BWB_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/1BWB_1539937370.png -------------------------------------------------------------------------------- /dataset/train/1G4J_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/1G4J_1539937370.png -------------------------------------------------------------------------------- /dataset/train/2PUI_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/2PUI_1539937370.png -------------------------------------------------------------------------------- /dataset/train/2TFY_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/2TFY_1539937370.png -------------------------------------------------------------------------------- /dataset/train/2ZWW_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/2ZWW_1539937370.png -------------------------------------------------------------------------------- /dataset/train/46AL_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/46AL_1539937370.png -------------------------------------------------------------------------------- /dataset/train/4MEM_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/4MEM_1539937370.png -------------------------------------------------------------------------------- /dataset/train/55IC_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/55IC_1539937370.png -------------------------------------------------------------------------------- /dataset/train/A41S_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/A41S_1539937370.png -------------------------------------------------------------------------------- /dataset/train/AVQK_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/AVQK_1539937370.png -------------------------------------------------------------------------------- /dataset/train/B647_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/B647_1539937370.png -------------------------------------------------------------------------------- /dataset/train/DRF0_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/DRF0_1539937370.png -------------------------------------------------------------------------------- /dataset/train/F3SR_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/F3SR_1539937370.png -------------------------------------------------------------------------------- /dataset/train/F4I1_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/F4I1_1539937370.png -------------------------------------------------------------------------------- /dataset/train/GQT4_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/GQT4_1539937370.png -------------------------------------------------------------------------------- /dataset/train/HQM1_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/HQM1_1539937370.png -------------------------------------------------------------------------------- /dataset/train/HWD5_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/HWD5_1539937370.png -------------------------------------------------------------------------------- /dataset/train/IDQY_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/IDQY_1539937370.png -------------------------------------------------------------------------------- /dataset/train/MFVG_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/MFVG_1539937370.png -------------------------------------------------------------------------------- /dataset/train/MLYM_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/MLYM_1539937370.png -------------------------------------------------------------------------------- /dataset/train/OIW9_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/OIW9_1539937370.png -------------------------------------------------------------------------------- /dataset/train/P9QN_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/P9QN_1539937370.png -------------------------------------------------------------------------------- /dataset/train/PY55_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/PY55_1539937370.png -------------------------------------------------------------------------------- /dataset/train/RB3A_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/RB3A_1539937370.png -------------------------------------------------------------------------------- /dataset/train/S50Z_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/S50Z_1539937370.png -------------------------------------------------------------------------------- /dataset/train/U206_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/U206_1539937370.png -------------------------------------------------------------------------------- /dataset/train/UV27_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/UV27_1539937370.png -------------------------------------------------------------------------------- /dataset/train/XK7E_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/XK7E_1539937370.png -------------------------------------------------------------------------------- /dataset/train/XY0K_1539937370.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/dataset/train/XY0K_1539937370.png -------------------------------------------------------------------------------- /docs/number.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/docs/number.png -------------------------------------------------------------------------------- /docs/number2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dee1024/pytorch-captcha-recognition/b87f83cb7f00b3785c4fae54bc9f59b2ccd4e054/docs/number2.png -------------------------------------------------------------------------------- /my_dataset.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import os 3 | from torch.utils.data import DataLoader,Dataset 4 | import torchvision.transforms as transforms 5 | from PIL import Image 6 | import one_hot_encoding as ohe 7 | import captcha_setting 8 | 9 | class mydataset(Dataset): 10 | 11 | def __init__(self, folder, transform=None): 12 | self.train_image_file_paths = [os.path.join(folder, image_file) for image_file in os.listdir(folder)] 13 | self.transform = transform 14 | 15 | def __len__(self): 16 | return len(self.train_image_file_paths) 17 | 18 | def __getitem__(self, idx): 19 | image_root = self.train_image_file_paths[idx] 20 | image_name = image_root.split(os.path.sep)[-1] 21 | image = Image.open(image_root) 22 | if self.transform is not None: 23 | image = self.transform(image) 24 | label = ohe.encode(image_name.split('_')[0]) # 为了方便，在生成图片的时候，图片文件的命名格式 "4个数字或者数字_时间戳.PNG", 4个字母或者即是图片的验证码的值，字母大写,同时对该值做 one-hot 处理 25 | return image, label 26 | 27 | transform = transforms.Compose([ 28 | # transforms.ColorJitter(), 29 | transforms.Grayscale(), 30 | transforms.ToTensor(), 31 | # transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) 32 | ]) 33 | def get_train_data_loader(): 34 | 35 | dataset = mydataset(captcha_setting.TRAIN_DATASET_PATH, transform=transform) 36 | return DataLoader(dataset, batch_size=64, shuffle=True) 37 | 38 | def get_test_data_loader(): 39 | dataset = mydataset(captcha_setting.TEST_DATASET_PATH, transform=transform) 40 | return DataLoader(dataset, batch_size=1, shuffle=True) 41 | 42 | def get_predict_data_loader(): 43 | dataset = mydataset(captcha_setting.PREDICT_DATASET_PATH, transform=transform) 44 | return DataLoader(dataset, batch_size=1, shuffle=True) -------------------------------------------------------------------------------- /one_hot_encoding.py: -------------------------------------------------------------------------------- 1 | # -*- coding: UTF-8 -*- 2 | import numpy as np 3 | import captcha_setting 4 | 5 | 6 | def encode(text): 7 | vector = np.zeros(captcha_setting.ALL_CHAR_SET_LEN * captcha_setting.MAX_CAPTCHA, dtype=float) 8 | def char2pos(c): 9 | if c =='_': 10 | k = 62 11 | return k 12 | k = ord(c)-48 13 | if k > 9: 14 | k = ord(c) - 65 + 10 15 | if k > 35: 16 | k = ord(c) - 97 + 26 + 10 17 | if k > 61: 18 | raise ValueError('error') 19 | return k 20 | for i, c in enumerate(text): 21 | idx = i * captcha_setting.ALL_CHAR_SET_LEN + char2pos(c) 22 | vector[idx] = 1.0 23 | return vector 24 | 25 | def decode(vec): 26 | char_pos = vec.nonzero()[0] 27 | text=[] 28 | for i, c in enumerate(char_pos): 29 | char_at_pos = i #c/63 30 | char_idx = c % captcha_setting.ALL_CHAR_SET_LEN 31 | if char_idx < 10: 32 | char_code = char_idx + ord('0') 33 | elif char_idx <36: 34 | char_code = char_idx - 10 + ord('A') 35 | elif char_idx < 62: 36 | char_code = char_idx - 36 + ord('a') 37 | elif char_idx == 62: 38 | char_code = ord('_') 39 | else: 40 | raise ValueError('error') 41 | text.append(chr(char_code)) 42 | return "".join(text) 43 | 44 | if __name__ == '__main__': 45 | e = encode("BK7H") 46 | print(decode(e)) --------------------------------------------------------------------------------