search

RuijieJ / pren

Code for "Primitive Representation Learning for Scene Text Recognition" (CVPR 2021)
Apache License 2.0
82 stars 17 forks source link

Datasets #4

Open YooWang opened 3 years ago

YooWang commented 3 years ago

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

RuijieJ commented 2 years ago

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

becxer commented 2 years ago

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?

RuijieJ commented 2 years ago

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.

becxer commented 2 years ago

Thank you!

Chang-shuaishuai commented 2 years ago

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?

RuijieJ commented 2 years ago

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

Chang-shuaishuai commented 2 years ago

哦哦，谢谢大佬，救命恩人呢

icecream-Tnak commented 2 years ago

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.

qyfff commented 2 years ago

image

qyfff commented 2 years ago

代码有地方要改吗

qyfff commented 2 years ago

有哥哥有数据集？

xushuanglong commented 1 year ago

请问大佬train_list里面具体应该怎么写，我写了图片及标签路径报语法错误，有没有train_list内容例子呀

saitejabandaru commented 6 months ago

Does anyone have a data set?

Yes please anyone having the exact dataset using in this paper??