conditional-flow-matching
conditional-flow-matching copied to clipboard
TorchCFM: a Conditional Flow Matching library
Hi, I am trying to use your package with the `from torchcfm.models.unet.unet import SuperResModel` and other custom models that have kwargs in their forward method, but I think that the...
This issue is opened for users to suggest improvements for the Flow Matching tutorial notebook.
Adding the diffusion-based distance used for the single-cell experiment. We approximate the heat kernel with Chebyshev polynomials. - [x] chebyshev approximation - [x] heat kernel + distance - [ ]...
Bumps [pytorch-lightning](https://github.com/Lightning-AI/lightning) from 1.8.3 to 2.2.0. Release notes Sourced from pytorch-lightning's releases. Lightning 2.2 Lightning AI is excited to announce the release of Lightning 2.2 :zap: Did you know? The...
Road to 1.1
I am opening this issue to discuss the road we should follow to the 1.1 version. Here is the list of the changes I would like to see: - [x]...
Bumps [torchmetrics](https://github.com/Lightning-AI/torchmetrics) from 0.11.0 to 1.3.0.post0. Release notes Sourced from torchmetrics's releases. New Image metrics & wrappers [1.3.0] - 2024-01-10 Added Added more tokenizers for SacreBLEU metric (#2068) Added support...
## What does this PR do? Add a script to generate multiple images for the CIFAR-10 examples Fixes #73 ## Before submitting - [x] Did you make sure **title is...
Updates the requirements on [torch](https://github.com/pytorch/pytorch) to permit the latest version. Release notes Sourced from torch's releases. PyTorch 2.1: automatic dynamic shape compilation, distributed checkpointing PyTorch 2.1 Release Notes Highlights Backwards...
The parameter `num_images` is currently unused in the cifar10 example https://github.com/atong01/conditional-flow-matching/blob/21cd0c888186f6e2b76deb393800361b8a850e9b/examples/cifar10/train_cifar10.py#L52 It would be great to have a `generate_cifar10.py` to generate a given number of images, as in the edm...
With POT 0.9.1 GPU memory is allocated on import in combination with deep learning packages see https://github.com/PythonOT/POT/issues/523 https://github.com/PythonOT/POT/issues/516 Recommend downgrading to POT < 0.9.1 for now.