Home
Softono
k

kerlomz

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Total Products
2

Software by kerlomz

captcha_trainer
Open Source

captcha_trainer

captchatrainer is a deep learning based CAPTCHA recognition training tool built on TensorFlow 1.14. It uses architectures like CNN5, ResNet50, and DenseNet combined with GRU, LSTM, or BiLSTM recurrent layers, and supports both CTC and CrossEntropy loss functions. The network extracts features through convolutional layers, predicts label distributions through recurrent layers, and converts predictions into final results through a transcription layer. The tool is designed to handle complex CAPTCHA scenarios including overlapping characters, perspective distortion, blur, and noise interference. It features a project-based management system where each image classification task gets its own independent workspace, allowing multiple models to coexist and be managed separately without modifying code. Key features include a pre-compiled Windows GPU version requiring no environment setup, incremental dataset additions without repackaging, flexible network configurations including CNN-only mode without recurrent layers,

ML Frameworks
3.2K Github Stars
captcha_platform
Open Source

captcha_platform

captchaplatform is a deployment platform for CAPTCHA recognition models based on CNN+BLSTM+CTC architecture. It is designed solely for serving trained models, not training them; companion project captchatrainer handles model training. The platform supports multiple serving frameworks including Tornado, Flask, Sanic, and gRPC, allowing flexible deployment options. It exposes HTTP and gRPC APIs that accept base64-encoded image data and return recognition results in JSON format containing the identified text, a status code, and a success flag. Key features include automatic model loading and hot-swapping. Users place trained model files (model.pb) in the graph folder and corresponding YAML configuration files in the model folder. The service automatically detects and loads new model configurations, enabling dynamic model management without service restart. Requirements include Python 3.9 with pip, and a virtual environment is recommended. The default requirements install the CPU version of TensorFlow; switching

ML Frameworks Screenshot & OCR
683 Github Stars