Guillaume Gaullier

Hello, > All single micrographs are different exposures. This is incompatible with the assumptions of noise2noise. You would need two micrographs of the exact same field of view, and even...

Maybe try [JANNI](https://github.com/MPI-Dortmund/sphire-janni)? It is also a noise2noise denoiser, but probably trained on a different training set than topaz denoise (not sure, you might have to dig this up from...

Seeing `MRC incompatible dtype`, I suggest you check two things: 1. are your MRC files float16 from RELION-4? 2. if so, is your topaz version older than commit 3428298e0745569929a9ed732d905f14c7044474 ?...

The commit adding support for `float16` is from April 2021, and [according to the conda repository](https://anaconda.org/tbepler/topaz) topaz was uploaded there only 15 months ago. So the version on conda most...

> Can cryodrgn take advantage of this patched version of scikit-learn? Training the model is the most computationally demanding process, by a very large margin, and doesn't use scikit-learn (it...

Being able to send a selection of particles back to cryoSPARC would be so useful! And I think it is best as only a selection, pointing to the original particles...

> Related to issues https://github.com/zhonge/cryodrgn/issues/72, https://github.com/zhonge/cryodrgn/issues/101, https://github.com/zhonge/cryodrgn/issues/148. Also #109

Seems like a great plan! Sorry to bring this up again (https://github.com/zhonge/cryodrgn/pull/70#issuecomment-941061328), maybe you already discussed it and chose to not use an external library, but just in case you...

I just tried this and it seems it is going to work! :tada: (The file was generated, but I will know for sure when I'm able to copy these newly...

Excellent! 🤩 Could you also add this for graph traversals?