Create custom convnet architecture using `arch`, `n_in` and `n_out`
create_cnn_model(
arch,
n_out,
cut = NULL,
pretrained = TRUE,
n_in = 3,
init = nn()$init$kaiming_normal_,
custom_head = NULL,
concat_pool = TRUE,
lin_ftrs = NULL,
ps = 0.5,
bn_final = FALSE,
lin_first = FALSE,
y_range = NULL
)
a model architecture
number of outs
cut
pretrained model or not
input shape
initializer
custom head
concatenate pooling
linear fiters
parameter server
batch normalization final
linear first
y_range
None