embeddings for PBMC3K based on 50 epochs of training by
torch-biggraph for 4780 highly variable genes on 2700 cells.
Note
Built using sce_to_embeddings with t3k
Examples
data(nn50)
names(nn50)
#> [1] "cemb" "gemb" "cents" "gents" "stats" "call" "config"
nn50$call
#> sce_to_embeddings(sce = t3k, workdir = "myfold50b", N_EPOCHS = 50L,
#> N_GENES = 5000L, N_GPUS = 0L, BATCH_SIZE = 1000L, pbg = pbg,
#> palib = palib)