pren Datasets

How could get the training datasets and testing datasets? Please.

Jul 26 '21 11:07 YooWang

Datasets can be downloaded from their official website. Some GitHub projects also provide their download link, such as https://github.com/HCIILAB/Scene-Text-Recognition

Oct 26 '21 02:10 RuijieJ

Hi, Im struggling with running the code. Do I have to convert manually from LMDB to "image/txt" files? Or could you provide the exact datasets (or link) in form of "image/txt" just to run the code?

Dec 29 '21 03:12 becxer

hi, if you want to run our code directly, you need to convert LMDB to image and txt files.

Or you can modify dataset.py, and read images and labels from LMDB, e.g., you may use the "lmdb" python lib.

Since the training set is too large, I cannot upload it. Sorry for that.

Dec 29 '21 07:12 RuijieJ

Thank you!

Dec 29 '21 07:12 becxer

你好，请问一下如果训练中文模型的话，它的数据集也需要 'sample' 和 ' .txt ' 这种吗？那它的 'alphabet.txt '这个文件该怎么做呢?

Dec 29 '21 09:12 Chang-shuaishuai

你好，请问一下如果训练中文模型的话，它的数据集也需要 'sample' 和 ' .txt ' 这种吗？那它的 'alphabet.txt '这个文件该怎么做呢?

数据集格式以及alphabet.txt和英文都是一样的，alphabet.txt里加入中文字符就行

Dec 30 '21 09:12 RuijieJ

哦哦，谢谢大佬，救命恩人呢

Dec 31 '21 08:12 Chang-shuaishuai

Thanks for your quality work. I would like to confirm that the results reported in the paper are the ICDAR 2013 857 and ICDAR 2015 1811 versions of the corresponding dataset. Because IC 13 and IC 15 both have two versions.