Deep Learning Slide Captcha

Python3WebSpider

Last update: Jan 2, 2023

Related tags

Deep Learning DeepLearningSlideCaptcha

Overview

滑动验证码深度学习识别

本项目使用深度学习 YOLOV3 模型来识别滑动验证码缺口，基于 https://github.com/eriklindernoren/PyTorch-YOLOv3 修改。

只需要几百张缺口标注图片即可训练出精度高的识别模型，识别效果样例：

克隆项目

运行命令：

git clone https://github.com/Python3WebSpider/DeepLearningSlideCaptcha.git

数据准备

使用 LabelImg 工具标注自行标注一批数据，大约 200 张以上即可训练出不错的效果。

LabelImg：https://github.com/tzutalin/labelImg

标注要求：

圈出验证码目标滑块区域的完整完整矩形，无需标注源滑块。
目标矩形命名为 target 这个类别。
建议使用 LabelImg 的快捷键提高标注效率。

环境准备

建议在 GPU 环境和虚拟 Python 环境下执行如下命令：

pip3 install -r requirements.txt

预训练模型下载

YOLOV3 的训练要加载预训练模型才能有不错的训练效果，预训练模型下载：

bash prepare.sh

下载完成之后会在 weights 文件夹下出现模型权重文件，供训练使用。

训练

本项目已经提供了标注好的数据集，在 data/captcha，可以直接使用。

如果要训练自己的数据，数据格式准备见：https://github.com/eriklindernoren/PyTorch-YOLOv3#train-on-custom-dataset。

当前数据训练脚本：

bash train.sh

实测 P100 训练时长约 15 秒一个 epoch，大约几分钟即可训练出较好效果。

测试

训练完毕之后会在 checkpoints 文件夹生成 pth 文件，可直接使用模型来预测生成标注结果。

此时 checkpoints 文件夹会生成训练好的 pth 文件。

当前数据测试脚本：

sh detect.sh

该脚本会读取 captcha 下的 test 文件夹所有图片，并将处理后的结果输出到 test 文件夹。

运行结果样例：

Performing object detection:
        + Batch 0, Inference Time: 0:00:00.044223
        + Batch 1, Inference Time: 0:00:00.028566
        + Batch 2, Inference Time: 0:00:00.029764
        + Batch 3, Inference Time: 0:00:00.032430
        + Batch 4, Inference Time: 0:00:00.033373
        + Batch 5, Inference Time: 0:00:00.027861
        + Batch 6, Inference Time: 0:00:00.031444
        + Batch 7, Inference Time: 0:00:00.032110
        + Batch 8, Inference Time: 0:00:00.029131

Saving images:
(0) Image: 'data/captcha/test/captcha_4497.png'
        + Label: target, Conf: 0.99999
(1) Image: 'data/captcha/test/captcha_4498.png'
        + Label: target, Conf: 0.99999
(2) Image: 'data/captcha/test/captcha_4499.png'
        + Label: target, Conf: 0.99997
(3) Image: 'data/captcha/test/captcha_4500.png'
        + Label: target, Conf: 0.99999
(4) Image: 'data/captcha/test/captcha_4501.png'
        + Label: target, Conf: 0.99997
(5) Image: 'data/captcha/test/captcha_4502.png'
        + Label: target, Conf: 0.99999
(6) Image: 'data/captcha/test/captcha_4503.png'
        + Label: target, Conf: 0.99997
(7) Image: 'data/captcha/test/captcha_4504.png'
        + Label: target, Conf: 0.99998
(8) Image: 'data/captcha/test/captcha_4505.png'
        + Label: target, Conf: 0.99998

样例结果：

协议

本项目基于开源 GNU 协议，另外本项目不提供任何有关滑动轨迹相关模拟和 JavaScript 逆向分析方案。

本项目仅供学习交流使用，请勿用于非法用途，本人不承担任何法律责任。

如有侵权请联系个人删除，谢谢。

FTIR-Deep Learning - FTIR Deep Learning With Python

CANDIY-spectrum Human analyis of chemical spectra such as Mass Spectra (MS), Inf

1 Jan 3, 2022

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution Figure: Example visualization of the method and baseline as a

16 Dec 23, 2022

PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper "Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis"

Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis This is a PyTorch implementation of the Deep Streaming Linear Discriminant

41 Dec 25, 2022

Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Deep Image Search - AI-Based Image Search Engine Deep Image Search is an AI-based image search engine that includes deep transfer learning features Ex

139 Jan 1, 2023

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O H2O is an in-memory platform for distributed, scalable machine learning. H2O uses familiar interfaces like R, Python, Scala, Java, JSON and the Fl

6.1k Jan 5, 2023

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

Machine Learning From Scratch About Python implementations of some of the fundamental Machine Learning models and algorithms from scratch. The purpose

21.8k Jan 9, 2023

A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

195 Dec 7, 2022

PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos

PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos. By adopting a unified pipeline-based API design, PyKale enforces standardization and minimalism, via reusing existing resources, reducing repetitions and redundancy, and recycling learning models across areas.

370 Dec 27, 2022

🧠 A PyTorch implementation of 'Deep CORAL: Correlation Alignment for Deep Domain Adaptation.', ECCV 2016

Deep CORAL A PyTorch implementation of 'Deep CORAL: Correlation Alignment for Deep Domain Adaptation. B Sun, K Saenko, ECCV 2016' Deep CORAL can learn

200 Dec 25, 2022

Comments

执行 sh train.sh 命令一直报错，你们有遇到吗

$ sh train.sh 2022-09-02 10:18:02.992340: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll 2022-09-02 10:18:04.602552: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set 2022-09-02 10:18:04.602591: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library nvcuda.dll 2022-09-02 10:18:04.629016: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1660 computeCapability: 7.5 coreClock: 1.815GHz coreCount: 22 deviceMemorySize: 6.00GiB deviceMemoryBandwidth: 178.86GiB/s 2022-09-02 10:18:04.629049: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll 2022-09-02 10:18:04.629066: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll 2022-09-02 10:18:04.629077: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll 2022-09-02 10:18:04.629087: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cufft64_10.dll 2022-09-02 10:18:04.629098: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library curand64_10.dll 2022-09-02 10:18:04.630010: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cusolver64_10.dll'; dlerror: cusolver64_10.dll not found 2022-09-02 10:18:04.630022: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusparse64_11.dll 2022-09-02 10:18:04.630028: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudnn64_8.dll 2022-09-02 10:18:04.630032: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1757] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2022-09-02 10:18:04.630287: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2022-09-02 10:18:04.630817: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-09-02 10:18:04.630825: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 2022-09-02 10:18:04.630838: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set 2022-09-02 10:18:07.565402: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll Namespace(batch_size=8, checkpoint_interval=1, compute_map=False, data_config='config/captcha.data', epochs=100, evaluation_interval=1, gradient_accumulations=2, img_size=416, model_def='config/yolov3-captcha.cfg', multiscale_training=True, n_cpu=8, pretrained_weights='weights/darknet53.conv.74') Traceback (most recent call last): File "train.py", line 118, in for batch_i, (_, imgs, targets) in enumerate(dataloader): File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 444, in iter return self._get_iterator() File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 390, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 1077, in init w.start() File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 112, in start self._popen = self._Popen(self) File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) BrokenPipeError: [Errno 32] Broken pipe

opened by Niklalala 1
训练后的图片有点毛病
自己训练的模型，总共用了200张图片训练的

训练完后，看着有一个固定偏差，貌似从中心位置开始画的框

使用模型后的图片变小了，原来 536 300，变成496 277

横坐标基本都偏离40（正好是原图片横坐标变小的尺寸），纵坐标变小30-35（原图变小23）

打印出来的结果，放在原图上是正确的。
opened by haidongsong 7

Deep Learning Slide Captcha

Related tags

Overview

滑动验证码深度学习识别

克隆项目

数据准备

环境准备

预训练模型下载

训练

测试

协议

You might also like...

FTIR-Deep Learning - FTIR Deep Learning With Python

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution

PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper "Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis"

Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

PyKale is a PyTorch library for multimodal learning and transfer learning as well as deep learning and dimensionality reduction on graphs, images, texts, and videos

🧠 A PyTorch implementation of 'Deep CORAL: Correlation Alignment for Deep Domain Adaptation.', ECCV 2016

Comments

执行 sh train.sh 命令一直报错，你们有遇到吗

训练后的图片有点毛病

Owner

Python3WebSpider

Deep Multi-Magnification Network for multi-class tissue segmentation of whole slide images

This is a virtual picture dragging application. Users may virtually slide photos across the screen. The distance between the index and middle fingers determines the movement. Smaller distances indicate click and motion, whereas bigger distances indicate only hand movement.

Makes patches from huge resolution .svs slide files using openslide

Discord-Protect is a simple discord bot allowing you to have some security on your discord server by ordering a captcha to the user who joins your server.

Layer 7 DDoS Panel with Cloudflare Bypass ( UAM, CAPTCHA, BFM, etc.. )

An auto discord account and token generator. Automatically verifies the phone number. Works without proxy. Bypasses captcha.

Ivy is a templated deep learning framework which maximizes the portability of deep learning codebases.

Deep learning (neural network) based remote photoplethysmography: how to extract pulse signal from video using deep learning tools

deep-table implements various state-of-the-art deep learning and self-supervised learning algorithms for tabular data using PyTorch.

Time-series-deep-learning - Developing Deep learning LSTM, BiLSTM models, and NeuralProphet for multi-step time-series forecasting of stock price.