All Projects → wushilian → Crnn_attention_ocr_chinese

wushilian / Crnn_attention_ocr_chinese

CRNN with attention to do OCR,add Chinese recognition

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Crnn attention ocr chinese

Easyocr
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stars: ✭ 13,379 (+4147.3%)
Mutual labels:  lstm, crnn, ocr
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-63.17%)
Mutual labels:  attention, crnn, ocr
learningspoons
nlp lecture-notes and source code
Stars: ✭ 29 (-90.79%)
Mutual labels:  lstm, attention
Tess4Android
A new fork base on tess-two and Tesseract 4.0.0
Stars: ✭ 31 (-90.16%)
Mutual labels:  ocr, lstm
Kraken
OCR engine for all the languages
Stars: ✭ 304 (-3.49%)
Mutual labels:  lstm, ocr
crnn.mxnet
crnn in mxnet.can train with chinese characters
Stars: ✭ 47 (-85.08%)
Mutual labels:  ocr, crnn
crnn.caffe
crnn.caffe
Stars: ✭ 76 (-75.87%)
Mutual labels:  lstm, crnn
datastories-semeval2017-task6
Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (-93.65%)
Mutual labels:  lstm, attention
Crnn Audio Classification
UrbanSound classification using Convolutional Recurrent Networks in PyTorch
Stars: ✭ 235 (-25.4%)
Mutual labels:  lstm, crnn
insightocr
MXNet OCR implementation. Including text recognition and detection.
Stars: ✭ 100 (-68.25%)
Mutual labels:  ocr, crnn
iPerceive
Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | Python3 | PyTorch | CNNs | Causality | Reasoning | LSTMs | Transformers | Multi-Head Self Attention | Published in IEEE Winter Conference on Applications of Computer Vision (WACV) 2021
Stars: ✭ 52 (-83.49%)
Mutual labels:  lstm, attention
automatic-personality-prediction
[AAAI 2020] Modeling Personality with Attentive Networks and Contextual Embeddings
Stars: ✭ 43 (-86.35%)
Mutual labels:  lstm, attention
BankCard-Recognizer
Identifying numbers from bankcard, based on Deep Learning with Keras [China Software Cup 2019]
Stars: ✭ 74 (-76.51%)
Mutual labels:  ocr, crnn
CRNN-OCR-lite
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Stars: ✭ 130 (-58.73%)
Mutual labels:  ocr, crnn
EBIM-NLI
Enhanced BiLSTM Inference Model for Natural Language Inference
Stars: ✭ 24 (-92.38%)
Mutual labels:  lstm, attention
Pytorch Seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+985.08%)
Mutual labels:  lstm, attention
Hierarchical-Word-Sense-Disambiguation-using-WordNet-Senses
Word Sense Disambiguation using Word Specific models, All word models and Hierarchical models in Tensorflow
Stars: ✭ 33 (-89.52%)
Mutual labels:  lstm, attention
Base-On-Relation-Method-Extract-News-DA-RNN-Model-For-Stock-Prediction--Pytorch
基於關聯式新聞提取方法之雙階段注意力機制模型用於股票預測
Stars: ✭ 33 (-89.52%)
Mutual labels:  lstm, attention
Icdar 2019 Sroie
ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction
Stars: ✭ 202 (-35.87%)
Mutual labels:  lstm, ocr
Rnn ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (-30.16%)
Mutual labels:  lstm, ocr

CRNN_Attention_OCR

CRNN with attention to do OCR,Chinese ocr in Chinese branch

network model

CRNN is base CNN,and BiLSTM with 256 hidden_units is encode network ,GRU with 256 hidden_units is decode network

how to use

put your image in 'train' dir,and image name should be like "xx_label_xx.jpg",Parameters are set in config.py,
and then just run the train.py

Dependency Library

TensorFlow >=1.2
opencv

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].