You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am generating simulated 2D projection images similar to section 5.1 in CryoDRGN paper. I have stored these 50k projection images in mrc file using mrc.write(‘particles.mrcs’,simulated_data,is_vol=0) command from CryoDRGN repo. (Specifically, I am trying to reproduce the simulation study mentioned in Section 5.1 of this paper). Now, I want to perform homogeneous reconstruction where the encoder is not required. So, I am considering using train_nn command instead of train_vae. However, this command has 'poses' as required parameter which does not make sense to me since in the paper it is not mentioned that you need poses. From my understanding, you need poses for heterogeneous reconstruction with pose supervision.
Could you please guide me on what command to use and what should be the parameters to reproduce the results in Section 5.1 of this paper? Also, I do not use abinit_homo command since it is based on CryoDRGN2 paper.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I am generating simulated 2D projection images similar to section 5.1 in CryoDRGN paper. I have stored these 50k projection images in mrc file using mrc.write(‘particles.mrcs’,simulated_data,is_vol=0) command from CryoDRGN repo. (Specifically, I am trying to reproduce the simulation study mentioned in Section 5.1 of this paper). Now, I want to perform homogeneous reconstruction where the encoder is not required. So, I am considering using train_nn command instead of train_vae. However, this command has 'poses' as required parameter which does not make sense to me since in the paper it is not mentioned that you need poses. From my understanding, you need poses for heterogeneous reconstruction with pose supervision.
Could you please guide me on what command to use and what should be the parameters to reproduce the results in Section 5.1 of this paper? Also, I do not use abinit_homo command since it is based on CryoDRGN2 paper.
Beta Was this translation helpful? Give feedback.
All reactions