tomodrgn.convergence.encoder_latent_shifts#

encoder_latent_shifts(workdir: str, outdir: str, plot_format: Literal['png', 'svg'], final_epoch: int) → None[source]#

Calculates and plots various metrics characterizing the per-particle latent vectors between successive epochs ranging between 0 and final_epoch.

Parameters:

workdir – path to directory containing tomodrgn training results
outdir – path to base directory to save outputs
plot_format – file format with which to save plots
final_epoch – the final epoch to analyze (typically the last epoch of training), zero-indexed. Note that because three epochs are needed to define the two inter-epoch vectors analyzed “per epoch”, the output contains metrics for E-2 epochs. Accordingly, plot x-axes are labeled from epoch 2 - epoch E.

Returns:

None