Unofficial PyTorch implementation of the paper, which integrates not only global semantic reasoning module but also parallel visual attention module and visual-semantic fusion decoder.the semanti reasoning network(SRN) can be trained end-to-end.

At present, the accuracy of the paper cannot be achieved. And i borrowed code from deep-text-recognition-benchmark

model

result

total_accuracy: 80.597

Feature

• predict the character at once time
• DistributedDataParallel training

Pytorch >= 1.1.0

1. download the evaluation data from deep-text-recognition-benchmark

2. download the pretrained model from Baidu, Password: d2qn

3. test on the evaluation data

python test.py --eval_data path-to-data --saved_model path-to-model

1. download the training data from deep-text-recognition-benchmark

2. training from scratch

python train.py --train_data path-to-train-data --valid-data path-to-valid-data

1. bert_ocr.pytorch
2. deep-text-recognition-benchmark
3. 2D Attentional Irregular Scene Text Recognizer
4. Towards Accurate Scene Text Recognition with Semantic Reasoning Networks

• use resnet for 1D feature not resnetFpn 2D feature
• use add not gated unit for visual-semanti fusion decoder

It is difficult to achieve the accuracy of the paper, hope more people to try and share