get a no learned accuracy in image classification

[Arielnabai]

For bugs or installation issues, please provide the following information.
The more information you provide, the more likely people will be able to help you.

Environment info

Operating System:

Compiler:

Package used (Python/R/Scala/Julia):

MXNet version:

Or if installed from source:

MXNet commit hash (git rev-parse HEAD):

If you are using python package, please provide

Python version and distribution:

If you are using R package, please provide

R sessionInfo():

Error Message:

Please paste the full error message, including stack trace.

Minimum reproducible example

if you are using your own code, please provide a short script that reproduces the error.

Steps to reproduce

or if you are running standard examples, please provide the commands you have run that lead to the error.

1.I prepared my network just as showed in#5019 mxnet / example / image-classification / symbols / and train my own data like #4681 mxnet / example / image-classification / train_cifar10.py
2.but I got a train accuracy about 1/num classes

What have you tried to solve it?

1.I have tried to change the lr and batch size but no help
2.
3.

[Arielnabai]

It seems I made a silly mistake that I prepare my data in a wrong way