Christoph Heindl

Is py-motmetrics missing any metrics/datasets?

9

Hey, this is a community question: are you aware of any metrics/datasets that **py-motmetrics** does not support out of the box, but that you wish it did? If yes, please...

See #110 for partial content.

Docker support

1

@jvlmdr, opening this issue to discuss whether or not we should keep docker support. IMHO, this feature is not maintained. @christosavg added it via PR #11 in the past, not...

Add more demosiacing methods | Merge with pytorch-debayer

1

## 🚀 Feature Add state-of-the-art demosaicing methods for bayer images. Here I'm not referring to deeply learned architectures. ## Motivation *kornia* currently implements a single [raw-to-rgb method](https://github.com/kornia/kornia/blob/master/kornia/color/raw.py) for different CFA...

A question on convergence of DSM

5

Hey, I'm currently tracing out the story of diffusion generative models and right now, I'm studying the denoising score matching objective (DSM). I've noticed that your multi-scale approach relies heavily...

Extend Benchmarks

8

More libraries to test against: pymatgen, centrosome See https://github.com/gatagat/lap/issues/9

Hey, I was just quickly browsing through the templates when I noticed that for the Autoencoder project the argparse parameter 'hidden_dim' is unused: https://github.com/PyTorchLightning/deep-learning-project-template/blob/faef5bbf4f3c392b9e4d71e606edaab5ce4d0aaf/project/lit_autoencoder.py#L54 I suspect this should be used...

Start examples/guideddr then in Blender switch tabs and observe timeouts.

See shlex shlex.quote(str(Path(r'c:\prog a\files')))