Attention-based Extraction of Structured Information from Street View Imagery：基于注意力的街景圖像提取結構化資訊

基于注意力的街景圖像提取結構化資訊

一種用于真實圖像文本提取問題的TensorFlow模型。

該檔案夾包含在FSNS資料集資料集上訓練新的注意OCR模型所需的代碼，以在法國轉錄街道名稱。 您還可以使用它來根據自己的資料進行教育訓練。

更多細節可以在我們的論文中找到：

“從街景圖像注意為基礎提取結構化資訊”

項目位址：

https://github.com/tensorflow/models/tree/master/attention_ocr

Attention-based Extraction of Structured Information from Street View Imagery

A TensorFlow model for real-world image text extraction problems.

This folder contains the code needed to train a new Attention OCR model on the FSNS dataset dataset to transcribe street names in France. You can also use it to train it on your own data.

More details can be found in our paper:

“Attention-based Extraction of Structured Information from Street View Imagery”

http://www.tensorflownews.com/