Rory Donovan-Maiye

TF model doesn't stay in memory with --save-every > 1

12

Hi, I'm running into a problem where training fails after the first epoch (or checkpoint, I'm not quite sure) and with this message: https://gist.github.com/donovanr/f1e728814776e3b26a70ad545093998c It looks like maybe the file...

## Use Case I want to run cells through IC that either have or have not been reflected ## Solution Add a column to the output that logs whether a...

Add more metadata to diagnostic sheets manifest

1

Adding a column for `ProteinDisplayName` or something like that would be great to be able to quickly sample one sheet per structure.

gan -> bVAE

Results: Figure 5

2

## Issue summary Fix up figure pretty significantly ## Details > had not appreciated that there were only 23 cells with the Golgi tag in the paclitaxel-treated group. I think...

Results: Figure 3

1

## Issue summary Fewer images / organelles / conditions ## Details > Too many sample images, way too teeny. Five columns should be enough in part B to make the...

Results: Content related to Fig. 3

1

## Issue summary feature histograms are all messed up ## Details > There is something deeply wrong with the output in part C. Look at “cell shape area” (which I...