Ellen Zhong

I can only speculate, but usually, the model will tend to learn larger features of variation first as they contribute more to the loss function, especially if you are in...

Maybe we could have a flag in `cryodrgn analyze` for the start index of the volume numbering.

Can you try again with --downsample 64? Good catch, we can adjust the default value for this option. Thanks! On Thu, Oct 27, 2022, 8:08 PM Oliver Clarke ***@***.***> wrote:...

Thanks for asking. 1) yes it will lead to a much longer training time than without pose search. Despite that, cryoDRGN2 is significantly faster and more accurate than cryoDRGN1's pose...

Related to issues #72, #101, #148.

One additional complexity is that particles are typically downsampled before training cryoDRGN, so the question is do we want the .cs file to point to the (new) downsampled particle stack...

Here's how to reimport a particle stack filtered by cryoDRGN back into cryoSPARC, while pointing to the original particles in the cryoSPARC project. 1. Export the original cryoSPARC particles from...

I added the above improvements to the figures and a new jupyter notebook which allows for customization in PR #228 Additional plots/visualizations on the wishlist: * Plot the latent embeddings...

Using sphinx to auto-generate help pages for docstrings in the commands/API seems helpful, but I do think gitbook is much easier for writing tutorials/user guides. Should we have both?

To make sure I am getting this right, it's not actually holding 16x50GB in memory, but if you're running `cryodrgn train_vae` via a slurm cluster, slurm's OOM handler will think...