Fixes #54

Fixes #59

Return the titin epitope tests back to the original more stringent threshold of 500nm (instead of 700nm)

Make test_imputation unit test fair by training the model with imputation for the same number of epochs as the model without imputation

Fix failing test test_class1_allele_specific_cv_and_train_command and switch downloads.yml to point to models without imputation for now

Lazily putting this all in one commit.

* infrastructure for downloading datasets and published trained models (the `mhcflurry-downloads` command)
* docs and scripts (in `downloads-generation`) to generate the pubilshed datsets and trained models
* parallelized cross validation and model training implementation, including support for imputation (based on the old mhcflurry-cloud repo, which is now gone)
* a single front-end script for class1 allele-specific cross validation and model training / testing (`mhcflurry-class1-allele-specific-cv-and-train`)
* refactor how we deal with hyper-parameters and how we instantiate Class1BindingPredictors
* make Class1BindingPredictor pickleable and remove old serialization code
* move code particular to class 1 allele-specific predictors into its own submodule
* remove unused code including arg parsing, plotting, and ensembles
* had to bump the binding prediction threshold for the Titin1 epitope from 500 to 700, as this test was sporadically failing for me (see test_known_class1_epitopes.py)
* Attempt to make tests involving randomness somewhat more reproducible by setting numpy random seed
* update README

added batch normalization between layers and changed default initialization to divide by sum of fan_in + fan_out instead of just fan_in

split up some of the class1_binding_predictor methods, moved code to training_helpers and Dataset, fixing broken unit tests