lovebobo
lovebobo
I have a question. in the file of cnn_letm_otc_ocr.oy , after cnn, the x.set_shape([FLAGS.batch_size, filters[3], 24]) is right? the time sequence should be the width which will be feed to...
I changed the code as @LevinJ ,but i got a error "tensorflow/core/util/ctc/ctc_loss_calculator.cc:144] No valid path found." I set the max_step as 128 and my input image is 32*192
我是华为mate 也是同样情况 求解决方案
me too ，，do you have the solution to that?
我也是，请问你有解决方案么？是不是需要root才行
Hello , I also meet the problem. Did you solve the difficult? THX
ahaha, Coffee time are too long~~