toolbox

The following applies to DDPG and TD3, and possibly other models. The following libraries were installed in a virtual environment:

numpy==1.16.4
stable-baselines==2.10.0
gym==0.14.0
tensorflow==1.14.0

Episode rewards do not seem to be updated in model.learn() before callback.on_step(). Depending on which callback.locals variable is used, this means that:

• episode rewards may n

Homer supports custom services, and provides a template to easily add new ones.

It could be great to add some more. Before starting to work on a custom service please open an issue to describe your idea and discuss about it.

Some ide

As the title says, this would be a parameter that allows the quality measurement parameters to be computed against a known image, rather than change per iteration.

Something like:

[img, qual] = SIRT(proj,geo,angles, 'QualMeas','RMSE','ground_truth',my_image)

According to the docs, filters are not implemented for FBP. However, TomoPy does not raise an error when you try to pass filter_name or filter_par with algorithm='fbp'. This would explain why, in my tests, choosing various filters for FBP did not change the reconstruction quality.

This definitely needs to be fixed