MalteDLuecken
MalteDLuecken
> If you only need the embedding of desc, you can set `do_tsne=False` and `do_umap=False`. Yes, I've already changed this :). I will test the code, make a PR and...
Thing seem to be running for me now, thanks! I just quickly wanted to highlight 2 things: 1. Installing DESC also requires `pydot` and `GraphViz` (not the python package, but...
It would be great if you could look over our PR here: https://github.com/theislab/scib/pull/131 Thanks!
Hi @eleozzr, We are still having an issue with saving the network weights. I have turned off saving weights via `save_encoder_weights=False`, but then I set `save_dir=tmp_dir` as you suggest in...
It would be great to get an input on the above question of how to turn off saving the weights.
thx, works!
Thanks for the quick reply. I just checked and it is zero. I've run quite a bit of analysis on this data already in scanpy, so I'm pretty sure it's...
Hi again. I've gotten garnett to work with count data input. But I was wondering if you could let me know how best to use pre-processed data. I have a...
I have found some instructions on how to load pre-processed data into a `cds` object [here](http://cole-trapnell-lab.github.io/monocle-release/docs/#choosing-a-distribution-for-your-data-required). The same page says the following: >estimateSizeFactors() and estimateDispersions() will only work, and are...
Thanks for the response! If I run `estimateSizeFactors()` before, would Garnett then use the size factors for a further normalization step while training the classifier or classifying the cells? I...