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
## 2.6829
## -0.4501
## 1.8055
## [ CPUFloatType{3,1} ]
##
## $b
## torch_tensor
## 0
## [ CPUFloatType{1} ]
# or individually
model$w
## torch_tensor
## 2.6829
## -0.4501
## 1.8055
## [ CPUFloatType{3,1} ]
## torch_tensor
## 0
## [ CPUFloatType{1} ]
# create an input tensor
x <- torch_randn(10, 3)
y_pred <- model(x)
## Calling forward!
## torch_tensor
## -3.2543
## -4.0736
## -0.4706
## -2.5269
## 3.6924
## 5.9955
## -3.4914
## 0.9271
## 1.3105
## 2.7783
## [ CPUFloatType{10,1} ]