get bug of memory leaks about deeplabv3-tensorflow HOT 6 OPEN

hello! I meet the same problem with you and it confused me several days, now i found it`s because in the function extract_batch ,too many data are read into the memory ,I decreased 512 to 128 and 4096 to 256,and the problem solved! hope that can help you

from deeplabv3-tensorflow.

my cudnn version is 6.0 , cuda is 8.0

from deeplabv3-tensorflow.

hello! I meet the same problem with you and it confused me several days, now i found it`s because in the function extract_batch ,too many data are read into the memory ,I decreased 512 to 128 and 4096 to 256,and the problem solved! hope that can help you

您好，我发现我改了之后还是内存爆了，如果方便的话，能给些建议吗？万分感激。

from deeplabv3-tensorflow.

hello! I meet the same problem with you and it confused me several days, now i found it`s because in the function extract_batch ,too many data are read into the memory ,I decreased 512 to 128 and 4096 to 256,and the problem solved! hope that can help you

您好，我发现我改了之后还是内存爆了，如果方便的话，能给些建议吗？万分感激。

你可以分步调试，就会找到出问题的那条语句

from deeplabv3-tensorflow.

hello! I meet the same problem with you and it confused me several days, now i found it`s because in the function extract_batch ,too many data are read into the memory ,I decreased 512 to 128 and 4096 to 256,and the problem solved! hope that can help you

您好，我发现我改了之后还是内存爆了，如果方便的话，能给些建议吗？万分感激。

你可以分步调试，就会找到出问题的那条语句

好滴，太谢谢您了！不过我还是没把代码跑通，我把那两个参数的值改得更小了，调试时sess.run loss就卡住了，没有显示报错，也没计算结果，并且也没有跳出运算，不知道是哪里出了问题。

from deeplabv3-tensorflow.

this is the official version of deeplab: https://github.com/tensorflow/models/tree/master/research/deeplab
you‘d best change the code.

from deeplabv3-tensorflow.