^o^
在你提供的数据集上,crnn能到达99.25左右,dense也能达到99.00左右,而no-lstm只能到达98.50左右,我看训练结果都比你的好,所以想问问你的测试集是你共享的么,我看check数据集太少了,估计你也是用test评估的吧,我用tensorflow实现的,谢谢
in ICPR MTWI 2018 Challenge 2, your result is F = 75.2， which do you select as backbone, resnet50,resnet101 or resnet152?
I find the fpn can't improve results，is it right
hi, i want to know your result in icdar2015 used fine-tune on other dataset,because myself result is 76% only training on icdar2015
what is the f-score about rctw2017, can you tell us some details?
你好，看你复现了mtcnn的各种网络结果，想问下lnet=24的原始网络，你有训练过么，还有能否测试一下精度