Hello,I have two questions.Because my dataset is too large,I am not sure of the N_cells_per_location.Could you please give me some advice?And can I reduce the batch_size like this to avoid the memory problem?I expect your reply.
mod.train(max_epochs=30000,
# train using full data (batch_size=None)
batch_size=256,
# use all data points in training because
# we need to estimate cell abundance at all locations
train_size=1
)
Hello,I have two questions.Because my dataset is too large,I am not sure of the N_cells_per_location.Could you please give me some advice?And can I reduce the batch_size like this to avoid the memory problem?I expect your reply.
mod.train(max_epochs=30000,
# train using full data (batch_size=None)
batch_size=256,
# use all data points in training because
# we need to estimate cell abundance at all locations
train_size=1
)