subnetwork_init_torch {deepregression} | R Documentation |
Initializes a Subnetwork based on the Processed Additive Predictor
Description
Initializes a Subnetwork based on the Processed Additive Predictor
Usage
subnetwork_init_torch(
pp,
deep_top = NULL,
orthog_fun = NULL,
split_fun = split_model,
shared_layers = NULL,
param_nr = 1,
selectfun_in = function(pp) pp[[param_nr]],
selectfun_lay = function(pp) pp[[param_nr]],
gaminputs,
summary_layer = model_torch
)
Arguments
pp |
list of processed predictor lists from |
deep_top |
In tf approach: keras layer if the top part of the deep network after orthogonalization; Not yet implemented for torch is different to the one extracted from the provided network |
orthog_fun |
function used for orthogonalization; Not yet implemented for torch |
split_fun |
function to split the network to extract head |
shared_layers |
list defining shared weights within one predictor; each list item is a vector of characters of terms as given in the parameter formula |
param_nr |
integer number for the distribution parameter |
selectfun_in , selectfun_lay |
functions defining which subset of pp to
take as inputs and layers for this subnetwork; per default the |
gaminputs |
input tensors for gam terms |
summary_layer |
torch layer that combines inputs (typically adding or concatenating) |
Value
returns a list of input and output for this additive predictor