captcha_trainer
Image verification model trainer
A framework for training image recognition models for verifying codes.
[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
3k stars
70 watching
823 forks
Language: Python
last commit: over 2 years ago
Linked from 1 awesome list
captcha-recognitionocrtensorflowtensorflow-tutorials
Related projects:
Repository | Description | Stars |
---|---|---|
| A recurrent neural network implementation optimized for speed and parallelizability | 31 |
| A C library for training and synthesizing recurrent neural networks | 900 |
| An object detection framework using deep convolutional networks and region proposal networks. | 2,716 |
| A deep learning implementation of a VRNN model for sequential data processing | 282 |
| A high-performance neural network inference framework supporting various deep learning frameworks and hardware platforms. | 4,435 |
| A framework for training and generating text sequences using multi-layer Recurrent Neural Networks | 11,668 |
| A Matlab toolbox providing a flexible implementation of deep learning architectures for sequences learning, including RNNs, LSTMs, and sequence-to-sequence models. | 80 |
| A custom implementation of Faster R-CNN with ResNet architecture and Online Hard Example Mining. | 207 |
| A Python implementation of a character-level Recurrent Neural Network (RNN) text generator using the MXNet Gluon framework. | 58 |
| A visual object detection system that combines region proposals with neural network features to improve detection performance. | 2,381 |
| Original models for deep residual networks as described in a 2015 research paper, implemented using Caffe. | 6,462 |
| An experimental implementation of Faster R-CNN object detection using TensorFlow | 2,340 |
| An implementation of Faster R-CNN object detection in PyTorch, modified from DenseCap. | 85 |
| A deep learning framework that enables sharing of residual units through collective tensor factorization to improve neural network performance. | 45 |
| Represents a neural network architecture with 1K layers, designed for image recognition tasks. | 909 |