rohitsaluja22

Hey @junyanz, this is Rohit. First, thanks for your code. It's really helpful. I trained your model on around 1.5 k images at A and B sides. I am observing...

Hi, Every font file comes with a gsub file which is a set of rules that define substituting consegutive glyphs with a joint glyph for example. Pygame ignores such gsub...

For Devanagari I have posted the solution in last part of Readme here (follow 7.0 and 7.1): https://github.com/rohitsaluja22/OCR-On-the-go

i am also facing the same issue, please respond

@vinjn will this work for model trained via original darknet code on https://pjreddie.com/darknet/?

@vinjn do you have any solution for the following issue? https://github.com/jing-vision/lightnet/issues/17

@Zardinality, I want a simple model with good loss function. In the end, I want samples from real distribution only. These models which you shared I guess give a style...

@Zardinality check this: https://arxiv.org/pdf/1801.07156.pdf I want to check out if vanila GAN can do this..

@devarshi16 will adding https://github.com/jing-vision/lightnet/tree/master/darknet_vs/ to linker path help, since it has file "yolo_cpp_dll.sln"?

A general way to look at dropout is that you are randomly dropping a fixed percentage(=dropout) of input edges to every node in the network. Anyone knows how this avoids...