Shaohui Ruan

@Sanster good job!

@YaroslavSchubert I am not sure about the reason, but it should occupy about >1.5G memory at least. So, I think that maybe it did not run on GPU,

@patterson163 most time is cost on some operations on cpu, so the speed may not varies widely

@hcnhatnam @NamNguyenThanh hi, the warning can be ignored, since vgg is only used as a pretrained model, and there remains some useless parameters. for the second problem, the training process...

@guddulrk hi, you should run split_label.py first to prepare the dataset. the input of split_label.py is x1,y1,x2,y2,x3,y3,x4,y4. and the output is text segment labelled in xmin,ymin,xmax,ymax. Then you can start...

@ZhuMingmin9123 Thanks for the sharing.

@hongdajun The image was not read in successfully. hence the shape of the image is None

@cks1999 replace [int_t](https://github.com/eragonruan/text-detection-ctpn/blob/37993c4b1a8e83cb6f5013efcff546d7ec87c16c/lib/utils/cython_nms.pyx#L28) to intp_t. if this does not work. try update your cython version

Thanks for the sharing.

@zunair11 your device may not have sufficient memory to run the code