-
Hi,
I've been reproducing your codes. And I have some questions about it.
How did you downsample 48kHz to 16kHz in the Valentini dataset?. I wonder which code you used.
Thanks.
-
Sketch of interface:
```
$ tensorboard daemon start # launches RustBoard in the background
$ tensorboard daemon add dir_a # watches a new log directory
$ tensorboard --daemon --bind_all # sta…
-
Thanks for your interesting work!
When I repeat your work on my dataset with the task of action segmentation, I have another two questions:
1. how to select the best backbone model? I try to use the…
-
We have been experimenting with how to style coverages in [CMSS](https://docs.ogc.org/per/18-025.html#StylingModel), e.g. being able to select which bands to use and how to use them and potentially co…
-
Hi,
I was hoping you would consider extending the rolling window functionality to time windows; as far as I can tell any rolling window functions simply work across a number of nearby points, and n…
-
on a large dataset occasionally we get an LLR error. This is probably due to downsampling messing with frequency numbers for LLR. minEventsPerUser wa added in April so this seem odd to be causing a pr…
-
+ [ ] **change `Snakefile` files and paths from underscores to dashes**: In `virus.snakefile` I switched all the paths that I was in control over to dashes instead of underscores. The snakemake rule n…
-
Is it because the external cropping loss of the cropping frame is ignored, so the outermost part of the generated picture is not very effective?How to solve it?
-
Originally reported on Google Code with ID 2696
```
Now we have 100%, 100/2, 100/3, 100/4, etc.
This is, however, quite huge waste of space. There is no real need in downsampling
quality in preview.…
-
https://github.com/holoviz/holoviews/pull/6059 added tsdownsample algorithms. We should, at a minimum, update the documentation to mention it.
Right now the other downsamples are mentioned here: h…