yizt/keras-ctpn
keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》;欢迎试用,关注,并反馈问题...
PythonApache-2.0
Issues
- 0
环境版本不适配
#32 opened by xingpeiran - 2
target.py正样本问题?不同的gt选择同一个anchor?
#30 opened by chenying99 - 2
请求requirements.txt
#31 opened by 4nthon - 9
- 2
- 2
能否提供模型的国内下载方式?谢谢
#27 opened by Nicole1130 - 1
请问跑了多少个epoch,最后loss是多少呢
#17 opened by kallyshall - 1
- 0
- 1
关于多分类的问题
#24 opened by kaixinbaba - 0
求助
#22 opened by kaixinbaba - 2
看源码时有一个疑问
#23 opened by kaixinbaba - 1
后处理速度非常慢,有没有什么优化的地方
#21 opened by PKQ1688 - 0
Change config.py file
#20 opened by Andiez-Nguyen - 2
Can i change the shape of input image? This model still work well, right?
#19 opened by NamNguyenThanh - 7
- 1
关于数据集所用的标注工具
#18 opened by 2017TJM - 2
Result in ICDAR2015
#2 opened by hcnhatnam - 5
- 2
I load pretrained model and met error: ValueError: Layer #142 (named "gru_forward"), weight <tf.Variable 'gru_forward_2/kernel:0' shape=(512, 192) dtype=float32_ref> has shape (512, 192), but the saved weight has shape (1024, 192).
#12 opened by hcnhatnam - 1
- 1
- 2
debug code
#11 opened by hcnhatnam - 1
why don't use validation_data in fit_generator
#10 opened by hcnhatnam - 4
- 2
请问image_annotation怎么制作,格式如何
#7 opened by RabbearSu - 1
- 2
deltas维度错误
#6 opened by RabbearSu - 2
- 12
side improvement isn't side-refinement ?
#3 opened by hcnhatnam - 1
Share trained model in Google Drive
#1 opened by hcnhatnam