Daniel Nouri

FWIW, `nolearn.lasagne.NeuralNet` now has a `partial_fit` method as discussed here, and it'll now also accept an output layer as its first argument (in addition of the funny list of tuples)....

When you read the [installation instructions](https://github.com/sermanet/OverFeat#installation), you'll notice that it says to run the `download_weights.py` script first.

The problem with this patch seems to be that coercion isn't performed very often. Imagine you have a test for a bit of code that produces the message "Hello, ${user}!"....

From looking at the test, I'm not sure what it's testing. Could you add a test for: self.assertEqual("This is Zope version 3.", inst)

I'm afraid that this is too many things in one. Some of these things are definitely improvements I want to merge. Others raise questions, and I'd like to be able...