forward {tfNeuralODE} | R Documentation |
Forward pass of the Neural ODE network
Description
Forward pass of the Neural ODE network
Usage
forward(model, inputs, tsteps, return_states = FALSE)
Arguments
model |
A keras neural network that defines the Neural ODE. |
inputs |
Matrix or vector inputs to the neural network. |
tsteps |
A vector of each time step upon which the Neural ODE is solved to get to the final solution. |
return_states |
A boolean which dictates whether the intermediary states between the input and the final solution are returned. |
Value
solution of the forward pass of Neural ODE
Examples
reticulate::py_module_available("tensorflow")
# example code
library(tensorflow)
library(keras)
OdeModel(keras$Model) %py_class% {
initialize <- function() {
super$initialize()
self$block_1 <- layer_dense(units = 50, activation = 'tanh')
self$block_2 <- layer_dense(units = 2, activation = 'linear')
}
call <- function(inputs) {
x<- inputs ^ 3
x <- self$block_1(x)
self$block_2(x)
}
}
tsteps <- seq(0, 2.5, by = 2.5/10)
true_y0 = t(c(2., 0.))
model<- OdeModel()
forward(model, true_y0, tsteps)
[Package tfNeuralODE version 0.1.0 Index]