No restore logic in evaluate.py

[renmengye]

I trained a MNIST network using train.py and saved in ./mnist folder.

In evaluate.py there is no logic that restores the saved network.

I printed the loss, it doesn't seem to decrease and I printed deltas, which are exactly the same as doing gradient descent (i.e. LSTM initialized at 0).

[ko3n1g]

can you elaborate on the solution? trying to get MNIST to work as well, but no luck so far. My tensorflow version is 1.5, dm-sonnet 1.10, running on GPU, and the mnist-bug (ticket #22) is implemented..