What does log_prob do?

pytorch probability-distribution
cerebrou picture cerebrou · Feb 11, 2019 · Viewed 9.2k times · Source

In some (e.g. machine learning) libraries, we can find log_prob function. What does it do and how is it different from taking just regular log?

For example, what is the purpose of this code:

dist = Normal(mean, std)
sample = dist.sample()
logprob = dist.log_prob(sample)

And subsequently, why would we first take a log and then exponentiate the resulting value instead of just evaluating it directly:

prob = torch.exp(dist.log_prob(sample))

Answer

cerebrou picture cerebrou · Feb 11, 2019

Part of the answer is that log_prob returns the log of the probability density/mass function evaluated at the given sample value.

Related questions

How to check if pytorch is using the GPU?

I would like to know if pytorch is using my GPU. It's possible to detect with nvidia-smi if there is any activity from the GPU during the process, but I want something written in a python script. Is there a …

Read More
How to initialize weights in PyTorch?

How to initialize the weights and biases (for example, with He or Xavier initialization) in a network in PyTorch?

Read More
How does the "view" method work in PyTorch?

I am confused about the method view() in the following code snippet. class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2,2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = …

Read More