Models: "ValueError: model_dir should be non-empty" for RNN for Drawing Classification

[noumanriazkhan]

System information

• What is the top-level directory of the model you are using: ~/networks/autodraw$
• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): 16.04
• TensorFlow installed from (source or binary): pip
• TensorFlow version (use command below):1.4.1
• Bazel version (if compiling from source):
• CUDA/cuDNN version: 8.0.61
• GPU model and memory: Tesla K80 / 24 GB
• Exact command to reproduce:

Describe the problem

I followed the tutorial as it is but its giving me "ValueError: model_dir should be non-empty".

[tatatodd]

This question is better asked on StackOverflow since it is not a bug or feature request. There is also a larger community that reads questions there. Thanks!

I also suggest you provide more details, e.g. a link to the documentation you're following, and the exact command that produced the error.

[noumanriazkhan]

The issue has been resolved by making a new directory and mentioning it in the --model_dir flag.

[jurschreuder]

this is referring to --output-dir, had this issue when the --output-dir was not local, but /home/me/etc/etc