Ellen Zhong

Summarizing the above discussion on a different pull request. Some cells in the jupyter notebooks assume poses include both rotations and translations, and that there are CTF parameters... which is...

Thanks Erik! The final iteration is always saved as `weights.pkl` and `z.pkl`, but we can also save out a `weights.N.pkl` and `z.N.pkl`. @vineetbansal

Hm, not sure why it suddenly died. To restart, you'll need to point it to the weights.pkl file, e.g. `--load train_vae_test_200k/weights.8.pkl`. @vineetbansal, we should check for the correct file type...

Can you include which version of the software you are running?

Assuming you haven't done any re-extractions before heterogeneous refinement, you could run downsample on the consensus particle stack. Could you send us the `.cs` file to see why the `blob/idx`...

Fixed in commit [ba7ae6d](https://github.com/zhonge/cryodrgn/commit/ba7ae6d011d1b1d70b90a3a8ccfc5c5669190c00), and updated the default decoder domain from Fourier to Hartley in [69251ff](https://github.com/zhonge/cryodrgn/commit/69251ff23b3e5a0506c730ea8e257877dba4ca05). Todo: the `PositionalDecoder` and `FTPositionalDecoder` models could be refactored (lots of repeat code).

@tomgoddard this is fantastic! Thank you! I agree with @priiteek; it would also be great to view the PC trajectories and even the `cryodrgn analyze_landscape` results, if possible. For viewing...

@vineetbansal could you add this feature? Thanks!

Hmm, ran into problems in training: ``` File "/Users/zhonge/dev/cryodrgn/cryodrgn/commands/train_vae.py", line 400, in main if in_dim % 8 != 0: NotImplementedError: The operator 'aten::remainder.Tensor_out' is not currently implemented for the MPS...

Particle selections can be converted to `.star` files with the script `write_starfile.py`. The `.star` file can then be re-imported to cryoSPARC. See this section of the tutorial for details and...