huyhoang17 / Vietnamese_handwriting_recognition
Licence: mit
[DEPRECATED] Vietnamese Handwriting Recognition with CRNN and CTC Loss
Stars: ✭ 23
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Vietnamese handwriting recognition
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (+404.35%)
Mutual labels: crnn, ctc
Crnn
A TensorFlow implementation of https://github.com/bgshih/crnn
Stars: ✭ 287 (+1147.83%)
Mutual labels: crnn, ctc
CRNN.tf2
Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2
Stars: ✭ 131 (+469.57%)
Mutual labels: ctc, crnn
Asrt speechrecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Stars: ✭ 4,943 (+21391.3%)
Mutual labels: ctc
Tensorflow end2end speech recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)
Stars: ✭ 305 (+1226.09%)
Mutual labels: ctc
Tf Crnn
TensorFlow convolutional recurrent neural network (CRNN) for text recognition
Stars: ✭ 275 (+1095.65%)
Mutual labels: crnn
pytorch convolutional rnn
PyTorch implementation of Convolutional Recurrent Neural Network
Stars: ✭ 117 (+408.7%)
Mutual labels: crnn
Ctcdecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python.
Stars: ✭ 529 (+2200%)
Mutual labels: ctc
Tensorflowasr
⚡️ TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
Stars: ✭ 400 (+1639.13%)
Mutual labels: ctc
Crnn attention ocr chinese
CRNN with attention to do OCR,add Chinese recognition
Stars: ✭ 315 (+1269.57%)
Mutual labels: crnn
Attention Ocr Chinese Version
Attention OCR Based On Tensorflow
Stars: ✭ 421 (+1730.43%)
Mutual labels: crnn
Ctcwordbeamsearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model for TensorFlow.
Stars: ✭ 398 (+1630.43%)
Mutual labels: ctc
Textclassificationbenchmark
A Benchmark of Text Classification in PyTorch
Stars: ✭ 534 (+2221.74%)
Mutual labels: crnn
Cortex License Plate Reader Client
A client to connect to cortex-provisioned infrastructure on AWS to do license plate identification in real time.
Stars: ✭ 268 (+1065.22%)
Mutual labels: crnn
Cnn lstm ctc ocr
Tensorflow-based CNN+LSTM trained with CTC-loss for OCR
Stars: ✭ 464 (+1917.39%)
Mutual labels: ctc
Cnn lstm ctc tensorflow
CNN+LSTM+CTC based OCR implemented using tensorflow.
Stars: ✭ 343 (+1391.3%)
Mutual labels: ctc
Vietnamese Handwriting Recognition
Dataset
- Vietnamese Handwriting Dataset: https://www.dropbox.com/s/zk82qkidkqma8bj/vn_handwriting_data.zip?dl=0
Command
export PYTHONPATH=path-to-project
cp src/example_config.py src/config.py
Result
-
Model trained with 25 epochs: https://github.com/huyhoang17/Colab_Temporary/blob/master/Training_CTC_Vietnamese_Recognition_25epochs.ipynb
-
[Overfitting model] Model trained with 10 epochs (initial weights from 25 epochs), reduced LR from 0.02 to 0.005: https://github.com/huyhoang17/Colab_Temporary/blob/master/%5BOverfitting%5DTraining_CTC_Vietnamese_Recognition_40epochs.ipynb
TODO
- Add Dockerfile
- Deploy simple demo with Tensorflow Serving
- Simple API
- Refactor code
- Add Visual Callback ✔️
- Train code with Colab's TPU?
- Convert to Pytorch code
Prevent Overfitting
- Data Augmentation ✔️
- Generate more data
- Simplifly the model
- Early Stopping
- Cross Validation
- Dropout (NN)
- Use Transfer Learing!
- ...
Reference
Colab Notebook:
Papers
- https://arxiv.org/pdf/1804.01527.pdf
- https://arxiv.org/abs/1801.08624
- https://arxiv.org/abs/1308.0850
CTC loss:
- https://www.dlology.com/blog/how-to-train-a-keras-model-to-recognize-variable-length-text/
- https://hackernoon.com/latest-deep-learning-ocr-with-keras-and-supervisely-in-15-minutes-34aecd630ed8
- https://github.com/SeanNaren/deepspeech.pytorch/blob/master/model.py
Kaggle ctc loss:
Explained ctc loss:
- https://gab41.lab41.org/speech-recognition-you-down-with-ctc-8d3b558943f0
- https://distill.pub/2017/ctc/
- https://stats.stackexchange.com/questions/320868/what-is-connectionist-temporal-classification-ctc
CTC loss param:
Overfitting
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].