ValueError: Error when checking target: expected activation_1 to have 3 dimensions, but got array with shape (356, 1)

Question

KeqiLi opened this issue 7 years ago · 2 comments

When I tried to run the codebase it returns such error.

I guess it's probably because of the updated Keras 2 API, but could you try to build it again?

Thanks a lot ;)

Answer 1 · 2017-11-04T04:32:34.000Z

I got these error using Keras 2 as well.

Downgrade to Keras 1.1.0 to solve the issue.

I recommend using a virtualevn.

Answer 2 · 2021-01-11T07:04:19.000Z

Are there any other way to fix this? I don't believe downgrade Keras to 1.x to is the only way to solve the issue.