Leon Oostrum

Support for filterbank header with FREQUENCY_START instead of fch1 + foff

1

Hi @scottransom, The filterbank header format with FREQUENCY_START \ FREQUENCY_END as output by e.g. SIGPROC's `splice` cannot be read by PRESTO. Maybe support for this could be added?

Add Tegra Observer to control clocks on Jetson devices

2

I've created an experimental `TegraObserver` that can monitor and control the GPU core clock on a Tegra device, similar to how NVML can do this for normal NVIDIA GPUs. I...

Currently DIANNA expects data in time-channel order for the timeseries explainers. However, e.g. the FRB data is in channel-time order. This can be handle by putting in some transposes, but...

We now run 3.9 and 3.11, see https://github.com/dianna-ai/dianna/blob/b656425d7e9eef066103cec47366e627f64712c6/.github/workflows/build.yml#L43 Before that, we tested on 3.8, 3.9, 3.10. Is there are reason we no longer test on 3.10? Shouldn't we at least...

When using many masks, pre-generating them all could use too much memory. In the dianna-deeprank branch (see https://github.com/dianna-ai/dianna/blob/c1823d7278be7602cba19ac56e69c5f13ec5a980/dianna/methods/rise.py#L190), we implemented a way to generate masks on the fly for RISE....

We support images with 1 or 3 channels, but no grayscale images without channels axis. This would be nice to support. See also the discussion in issue #222.

To avoid having to edit the contents of docs/tutorials when adding/changing a tutorial notebook, we could automatically generate the files in docs/tutorials as part of the doc building CI.

The heatmap produced in the rise imagenet notebook varies quite a bit when re-running the notebook due to the randomness of the masks. When someone runs the tutorial, they will...

Replace model runner function by preprocessing function

1

In a lot of the more recent tutorials a `run_model` function is defined, with reasoning such as "A runner function is required since the model works with input in the...

In e.g. the lime text tutorial, DIANNA is run separately for each class. This is unnecessary, wwe can also run it once and request heatmaps for multiple classes. In my...