flowtorch
flowtorch copied to clipboard
This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a community of users and contributors by focusing initially on c...
### Issue Description Hello, I am trying to compuse a bijector with `AffineAutoregressive` and `Tanh`. The flow crashes in this case when computing the log_prob. ### Steps to Reproduce ```python...
### Issue Description A clear and concise description of the issue. If it's a feature request, please add [Feature Request] to the title. Not able to get all the data...
### Issue Description The Multivariate Bijectors tutorial notebook has an issue: someone hit a keyboard interrupt and so it's not complete. ### Steps to Reproduce No steps to reproduce needed,...
Adds Coupling layers. ### Test plan ```python from flowtorch.parameters.coupling import DenseCoupling, ConvCoupling from flowtorch.bijectors.coupling import CouplingBijector as Coupling, ConvCouplingBijector import torch torch.set_default_dtype(torch.double) def test(): d = DenseCoupling() c = Coupling(d)...
### Motivation We introduce the Split Bijector, which allows to split a tensor in half, process one half through a sequence of transformations and normalize the other. ### Changes proposed...
### Motivation Proposes a 1x1 convolution bijector. ### Test Plan ```python from flowtorch.bijectors import Conv1x1Bijector import torch def test(LU_decompose, zero_init): c = Conv1x1Bijector(LU_decompose=LU_decompose, zero_init=zero_init) c = c(shape=torch.Size([10, 20, 20])) for...
A splitting bijector splits an input `x` in two equal parts, `x1` and `x2` (see for instance Glow paper):  Of those, only `x1` is passed to the remaining part...
Summary: Enabled Google Analytics for the Docsaurus v2 website to get automated repo checkup to pass Differential Revision: D32608371
Implement these three important Bijectors. Should probably start with the most important one, `reshape`