The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
This vignette showcases the basic functionality of distributions in torch. Currently the distributions modules are considered ‘work in progress’ and are still experimental features in the torch package. You can see the progress in this link.
The distributions modules in torch are modelled after PyTorch’s distributions module which in turn is based on the TensorFlow Distributions package.
This vignette is based in the TensorFlow’s distributions tutorial.
Let’s start and create a new instance of a normal distribution:
We can draw samples from it with:
or, draw multiple samples:
We can evaluate the log probability of values:
or, evaluate multiple log probabilities:
A distribution can take a tensor as it’s parameters:
This object represents 3 independent Bernoulli distributions, one for each element of the tensor.
We can sample a single observation:
or, a batch of n
observations:
The log_prob
method of distributions can be
differentiated, thus, distributions can be used to train models in
torch.
Let’s implement a Gaussian linear model, but first let’s simulate some data
and plot:
We can now define our model:
GaussianLinear <- nn_module(
initialize = function() {
# this linear predictor will estimate the mean of the normal distribution
self$linear <- nn_linear(1, 1)
# this parameter will hold the estimate of the variability
self$scale <- nn_parameter(torch_ones(1))
},
forward = function(x) {
# we estimate the mean
loc <- self$linear(x)
# return a normal distribution
distr_normal(loc, self$scale)
}
)
model <- GaussianLinear()
We can now train our model with:
opt <- optim_sgd(model$parameters, lr = 0.1)
for (i in 1:100) {
opt$zero_grad()
d <- model(x)
loss <- torch_mean(-d$log_prob(y))
loss$backward()
opt$step()
if (i %% 10 == 0)
cat("iter: ", i, " loss: ", loss$item(), "\n")
}
We can see the parameter estimates with:
and quickly compare with the glm()
function:
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.