Aurora Cramer

https://zenodo.org/record/3694384

Adding SSLR dataset

2

https://www.idiap.ch/en/dataset/sslr

Downloads fail when the network connection is interrupted, resulting in a `ContentTooShortError: `. It would be helpful for the user to increase the timeout when calling `dataset.download()` so the download...

So it's easier for people to find out more about the datasets from the docs

Add dataset sizes (in GB) in documentation

1

It would be helpful to have an idea of how much disk space you need for the datasets if space is an issue

It seems like `compute_output_shape` assumes that the pooling size is always 2, so the output shape is incorrect with other pooling sizes.

It might be useful to have a histogram view in order to see the distribution of tags within a list (or board), or the distribution of counts for cards in...

## US8K * [x] L3 embedding / linear model / music set * [x] L3 embedding / melspec1 / music set * [ ] L3 embedding / melspec2 / music...

## US8K * [x] L3 embedding / linear model / music set * [x] L3 embedding / melspec1 / music set * [ ] L3 embedding / melspec2 / music...

First install the latest version of `kapre` by running (in your conda environment) `pip install --upgrade kapre`. For all jobs, use [jobs/l3embedding-train-melspec2-03202018.sbatch](https://github.com/marl/l3embedding/blob/master/jobs/l3embedding-train-melspec2-03202018.sbatch) as a template, modifying it in the specified...