[WSRI26] Neural Net Encoding Methods for 3D Geometry

DOWNLOAD-DESKTOP-NOTEBOOK.nb (8.64 MB)

12 Likes

I suggest that this could be extended to 4 dimensions (x, y, z, and t) for your movie making interest.

1 Like

news-congrads-kkluyshnik-02-04-19.jpg – you have earned Featured Contributor Badge 2015-11-02_10-07-11.png
Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!

1 Like

Hi Caden,
I really enjoyed your presentation. When I tried to redo your work I get stuck after the network has been trained.

In[38]:= voxelTrainedNet = voxelTrainingResults["TrainedNet"]

How exactly can I use this trained network to recreate the shapes? Thank you, Johannes.

Hello!

NetTrainResultsObjects are quite large, so my original results are stored in a cloud object that can be imported. Depending on your specific error, you may need to make sure that your results object is using the same name as what the rest of the code expects.

1 Like