TextBoxes

TextBoxes copied to clipboard

Hello, author, I can't download this dataset. Can you share it with me？ [email protected]

heping0307

Fine tuning on custom dataset: converting to LMDB

5

I have a custom dataset which is a modified version of the ICDAR 2013 training dataset for training(also a separate modified ICDAR2013 for testing), so I would like to fine-tune...

gaalejandre

Failed to run make -j8

1

 Can someone help me, where am I making mistake.

eravallirao

cannot find -lopencv_imgcodes

1

I've already installed opencv ,but it still has error "/usr/in/ld:cannot fint -lopencv_imgcodecs","/usr/bin/ld:cannot find -lopencv videoio" Who can help me solve this problem?Thank you very much

BabyBottle

error run create_data.sh , only generate the Soft connection，the size is 57 bytes , but did not genereate the actual lmdb

12

error run create_data.sh , only generate the Soft connection，the size is 57 bytes , but did not genereate the actual lmdb . this is the ｒｅｓｕｌｔ of running the create_data.sh...

19931991

fine-tuning training prolem

4

@MhLiao hi, i have a problem during training. First, I learned with SynthText data. I learned by changing two learning rates with reference to your paper. so, see logs.. (examples)...

peternara

I have some questions while reading your code with paper. 1. The `conf` head in your paper use 1x1 size, but in the code was all 1x5 2. The prior...

FantasyJXF

作者您好！ 最近在学习目标检测，非常感谢您在此项目做的贡献。现在有一个问题想请教你：TextBoxes_icdar13.caffemodel这个模型是分别在Synthtext和icdar13两个数据集上预训练，还是只是在icdar13上预训练了？ 期待百忙之中给予回答帮助，谢谢！

mrlihellohorld

testing results on Total-Text

1

你好，請問一下在end to end Text spotting for Total-Text dataset, 對於Textboxes和Mask Text-Spotter的end to end結果，你們使用的是single-scale testing 還是multi-scale testing?

wqtwjt1996

I re-implement this model by torch. But when i train this model using Adam, loss become nan soon although i try several learning rates. So I want to ask some...

ZeroOne96