nflows
nflows copied to clipboard
Normalizing flows in PyTorch
I am testing out a few different types of architectures for training normalising flows, and I am running into an unexpected bug. The first architecture uses a `MaskedPiecewiseRationalQuadraticAutoregressiveTransform`: ``` transforms...
I've trained a conditional MAF with two additional context variables, pretty much identical to the two-moon example in the repo. However, I'm having some trouble coercing that context into the...
From PyTorch 1.11 docs: [link](https://pytorch.org/docs/stable/generated/torch.triangular_solve.html) > UserWarning: torch.triangular_solve is deprecated in favor of torch.linalg.solve_triangular and will be removed in a future PyTorch release. > torch.linalg.solve_triangular has its arguments reversed and...
I wanna use this code to predict stocks, but my data shape is (n,6),the example moons has only dimension 2, I can't do this: ``` xline = torch.linspace(-1.5, 2.5, 100)...
Hello, The dependencies `matplotlib`, `tensorboard` and `tqdm` are installed by `setup.py` (and `environment.yml`) even though they are not used by `nflows`. They should be removed. https://github.com/bayesiains/nflows/blob/ac0bf432fc7904458a933ed14180f0ac26e3f93d/setup.py#L22-L26 It should be noted...
Hi! I am trying to reproduce some benchmark results such as the results from the original MAF paper https://arxiv.org/pdf/1705.07057.pdf . For instance, MAF with 5 layers on HEPMASS achieves a...
First of all thanks for providing this awesome library. In our applications, it is sometimes beneficial to initialize transforms as the identity. We usually achieve this by setting all parameters...
When we are setting the "learn_temperature" to False, the temperature is not sent to the correct device when trying to train on the GPU. By registering the temperature as a...
Hi, Since the `CouplingTransform` class in `nflows.transforms.coupling` module only supports a 1-d mask that splits data along the channel dimension, I am wondering how I would go about implementing the...