Jcmels

@kcauchy 单线程生成验证码图片，train的过程调用都是看TensorFlow自己去调用的，你加BN之后可以很快得到想要的结果。可能你CPU太强，我用imac的i5去train的，几乎满载

哈哈开个脑洞，如果刘海屏，水滴屏能直接适配就牛逼了~感谢Jess神开发如此低成本的适配框架

Google在TensorFlow的demo里有个效率很高的算法 ``` public class ImageUtils { // This value is 2 ^ 18 - 1, and is used to clamp the RGB values before their ranges // are normalized to...

@leslietso @huythach Hi all,I also have this issues--" Could not create Tensorflow Graph: Invalid argument: NodeDef mentions attr 'Tshape' not in Op output:T; attr=T:type>; " Now tensorflow update to r1.0.I...

@leslietso Thanks for your share "jni-build".My app can run now.But I want to know that how to fix it.How to build tensorflow can get genfiles's file?

hello?any update?

@Cuky88 I use Google's model --object_detection to train it