airaria / Captcharecognition
Licence: mit
End-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别
Stars: ✭ 97
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Captcharecognition
Cnn lstm for text classify
CNN, LSTM, NBOW, fasttext 中文文本分类
Stars: ✭ 90 (-7.22%)
Mutual labels: cnn, rnn, attention
Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-49.48%)
Mutual labels: cnn, rnn
Deepfakes video classification
Deepfakes Video classification via CNN, LSTM, C3D and triplets
Stars: ✭ 24 (-75.26%)
Mutual labels: cnn, rnn
Rnn Theano
使用Theano实现的一些RNN代码，包括最基本的RNN，LSTM，以及部分Attention模型，如论文MLSTM等
Stars: ✭ 31 (-68.04%)
Mutual labels: cnn, rnn
Attention Over Attention Tf Qa
论文“Attention-over-Attention Neural Networks for Reading Comprehension”中AoA模型实现
Stars: ✭ 58 (-40.21%)
Mutual labels: rnn, attention
Tensorflow cookbook
Code for Tensorflow Machine Learning Cookbook
Stars: ✭ 5,984 (+6069.07%)
Mutual labels: cnn, rnn
Deeplearning Nlp Models
A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.
Stars: ✭ 64 (-34.02%)
Mutual labels: cnn, attention
Machine Learning
My Attempt(s) In The World Of ML/DL....
Stars: ✭ 78 (-19.59%)
Mutual labels: rnn, attention
Attend infer repeat
A Tensorfflow implementation of Attend, Infer, Repeat
Stars: ✭ 82 (-15.46%)
Mutual labels: rnn, attention
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-76.29%)
Mutual labels: cnn, rnn
Eda nlp
Data augmentation for NLP, presented at EMNLP 2019
Stars: ✭ 902 (+829.9%)
Mutual labels: cnn, rnn
Attentive Neural Processes
implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
Stars: ✭ 33 (-65.98%)
Mutual labels: rnn, attention
Tf Rnn Attention
Tensorflow implementation of attention mechanism for text classification tasks.
Stars: ✭ 735 (+657.73%)
Mutual labels: rnn, attention
Time Attention
Implementation of RNN for Time Series prediction from the paper https://arxiv.org/abs/1704.02971
Stars: ✭ 52 (-46.39%)
Mutual labels: rnn, attention
Multi Class Text Classification Cnn Rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
Stars: ✭ 570 (+487.63%)
Mutual labels: cnn, rnn
Text Classification
Implementation of papers for text classification task on DBpedia
Stars: ✭ 682 (+603.09%)
Mutual labels: cnn, attention
Nlp overview
Overview of Modern Deep Learning Techniques Applied to Natural Language Processing
Stars: ✭ 1,104 (+1038.14%)
Mutual labels: cnn, rnn
Sleepeegnet
SleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
Stars: ✭ 89 (-8.25%)
Mutual labels: cnn, rnn
CaptchaRecognition
End-to-end variable length Captcha recognition using CNN+RNN+Attention or CTC. 端到端的不定长验证码识别
encoder: CNN+RNN or CNN
decoder: two types of attention +no attention
目前encoder端可以选择使用CNN+RNN或CNN；decoder端有两种attention方式+不使用attention。
update(2017-10-27)
- RNN+CTC added. 新增了 CNN+RNN + CTC 的验证码识别。
Usage
Put your font file in fonts directory, and change the font file's name in line 173 of GenCaptcha.py.
To generate training data in data/, run python GenCaptcha.py.
Run python main.py to train.
把字体文件放入fonts文件夹，并修改GenCaptcha.py中第173行的字体文件名。
运行 python GenCaptcha.py ，在data/下生成数据集captcha.npz和captcha.vocab_dict。
（GenCaptcha.py中还提供了生成tfrecord文件的函数。）
运行 python main.py训练。
Using CTC
Install warp_ctc for pytorch, and run python ctcmain.py.
按照上一节的步骤生成数据后，运行 python ctcmain.py.
Results
results of using CTC (accuracy reaches 0.95 on test set)：
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].