Generate embeddings with bug-fixes

Nobody has claimed this yet.

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

## ESC-50
* [x] L3 embedding / linear model / music set
* [x] L3 embedding / melspec1 / music set
* [ ] L3 embedding / melspec2 / music set
* [x] L3 embedding / linear model / env set
* [x] L3 embedding / melspec1 / env set
* [ ] L3 embedding / melspec2 / env set

## DCASE 2013
* [x] L3 embedding / linear model / music set
* [x] L3 embedding / melspec1 / music set
* [ ] L3 embedding / melspec2 / music set
* [x] L3 embedding / linear model / env set
* [x] L3 embedding / melspec1 / env set
* [ ] L3 embedding / melspec2 / env set

## Instructions
To generate samples (for L3 embedding models), make edit or make a copy of `jobs/generate_embedding_samples_array_.sbatch` In there, you'll want to make the following changes:

0. **Make sure that the embedding model path follows the convention** `/embedding////model_best_valid_accuracy.h5`. **The code assumes this convention to be followed.**
1. Change the email to your email
2. Change the anaconda environment name
3. Change `SRCDIR` to whatever directory the `l3embedding` repository is in
4. Change `L3_MODEL_PATH` to the path of the `.h5` file of the model you want to use.
5. Change `L3_POOLING_TYPE` to `original`.
6. Change `OUTPUT_DIR` to your general experiment output directory. A subdirectory called `features` will be created here for the embedding output.
7. Add any additional command line arguments to the script call. Take a look at `05_generate_embedding_samples.py` for the options. (shouldn't need to do for this though)
8. Run `sbatch --array=1- generate_embedding_samples_array_.sbatch`
- is 10 for US8K, 5 for ESC-50, and 2 for DCASE

Start with the unchecked combinations in the US8K, ESC-50, and DCASE 2013 checklists, then inspect the matching jobs/generate_embedding_samples_array_.sbatch files and 05_generate_embedding_samples.py. Follow the listed environment, repository, model-path, pooling, and output settings before submitting the arrays. Done means all listed melspec2 music and environmental embeddings have been generated.

Written by the indexing model from the issue text.