commaai / commaai/research

ValueError: Shapes are not compatible when training transition model after autoencoder trained

Open
#22 26 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
4.1k
Forks
1.2k
PR merge metrics
No merged PRs in 30d

Description

Hi,

I trained the autoencoder successfully. However, when I was doing followup steps in training the transition model, I had the problem below.
![image](https://cloud.githubusercontent.com/assets/7718748/18214006/b5a04480-70ff-11e6-8329-9bc94b3dd288.png)

Thanks a lot for any help!

BTW, I didn't change any code.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.