mmocr

mmocr copied to clipboard

DBnet 使用ploy方式，检测弯曲文本，有没有预训练模型呀

10

由于样本数据比较少，只有400张，单纯的用resnet18模型做预训练模型太难收敛了，如果用quad没有问题，但是样本大部分是弯曲样本，所以来请教一下，谢谢！

Tomhouxin

training synthtext, encounting OOM

2

Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...

liuheng92

This is a description of our projects released via [GitLink Code Camp](https://mp.weixin.qq.com/s/upVI-2TQ0ezQGpzhDiF3Pg), which are intended for Chinese students. ## 题目名称 基于 MMOCR 实现前沿 OCR 算法 ## 题目描述 ### 题目简介 MMOCR...

gaotongxiao

ValueError: too many dimensions 'str' Trying to train KIE on custom Dataset

2

Hello . i faced a problem when trying to train my custom KIE dataset after the first epoch I got this error message : ValueError: too many **Reproduction** !python tools/train.py...

hmiche

How to make Training data for Training key-information-extraction

4

Hello guys . how can i make ma training set to train my own custom key-information-extraction is there any available tools to do that ?

hmiche

请问关于synthtext的检测部分如何进行

6

不知怎么读取mdb格式，为啥不弄成json格式呢

ocrhei

[DBNET]-Bad performance on long text detection

13

Hi, thanks for your great job. I'm using R50DCN dbnet for chinese text detection. I used about 10k pictures for training based on the [pretrain model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_2e_synthtext_20210325-aa96e477.pth). When testing, long text...

fatfishZhao

Updated the det.md Chinese translation

5

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

EugeneWong2002

[Model] ABCNet Recognizer

1

This PR is based on #746 and #747. This recognizer is standalone and is ready to be trained on any text recognition dataset. # Modifications 1. A new `NLLLoss` module...

gaotongxiao

[Model] Add ABCNet recog decoder and fix docstring in CRNN

1

## Modification 1. Renamed `mmocr.models.textrecog.layers.lstm_layer` to `mmocr.models.textrecog.layers.rnn_layers` 2. Added `AttentionGRUCell` to `mmocr.models.textrecog.layers.rnn_layers` 3. Added ABCNet's recognition decoder 4. Fixed docstring in CRNN ## BC-breaking Users who have imported anything from...

gaotongxiao