TypeError: 'skimage' backend only supports 2d parallel geometries

[pygabc1]

Hi, I am learning your paper and code.
When I run partially_learned_gradient_descent_head.py, I have this error message ;
TypeError: 'skimage' backend only supports 2d parallel geometries
Google don't have enough information, and how to settle it? Thanks.

[adler-j]

You need to install ASTRA to be able to run the code. After installing it, you should be fine.

[pygabc1]

You need to install ASTRA to be able to run the code. After installing it, you should be fine.

Dear Adler,
Thank you for your reply.
I am using colab.
I installed ASTRA through your website, [Minimal example of running ASTRA + ODL in colab], but I still have this error.
[AttributeError: module 'odl.tomo' has no attribute 'FanFlatGeometry']
Referring your website, I did
[$ pip install https://github.com/adler-j/odl/archive/tensorflow_support.zip], but the URL does not work for me.
Thanks again.

[adler-j]

How did you install ODL? I think at this point it should be possible to work from head at GitHub.

[pygabc1]

This is what I installed.

......
......