library(torch)
# creates example tensors. x requires_grad = TRUE tells that
# we are going to take derivatives over it.
dense <- nn_module(
clasname = "dense",
# the initialize function tuns whenever we instantiate the model
initialize = function(in_features, out_features) {
# just for you to see when this function is called
cat("Calling initialize!")
# we use nn_parameter to indicate that those tensors are special
# and should be treated as parameters by `nn_module`.
self$w <- nn_parameter(torch_randn(in_features, out_features))
self$b <- nn_parameter(torch_zeros(out_features))
},
# this function is called whenever we call our model on input.
forward = function(x) {
cat("Calling forward!")
torch_mm(x, self$w) + self$b
}
)
model <- dense(3, 1)
## Calling initialize!
# you can get all parameters
model$parameters
## $w
## torch_tensor
## -0.2114
## 1.9879
## -0.8693
## [ CPUFloatType{3,1} ][ requires_grad = TRUE ]
##
## $b
## torch_tensor
## 0
## [ CPUFloatType{1} ][ requires_grad = TRUE ]
# or individually
model$w
## torch_tensor
## -0.2114
## 1.9879
## -0.8693
## [ CPUFloatType{3,1} ][ requires_grad = TRUE ]
## torch_tensor
## 0
## [ CPUFloatType{1} ][ requires_grad = TRUE ]
# create an input tensor
x <- torch_randn(10, 3)
y_pred <- model(x)
## Calling forward!
## torch_tensor
## -2.4000
## -0.6041
## 2.4616
## -7.1394
## -2.4070
## -0.8684
## -1.0604
## -1.3762
## -1.7317
## 4.6042
## [ CPUFloatType{10,1} ][ grad_fn = <AddBackward0> ]