ikostrikov / pytorch-meta-optimizer

A PyTorch implementation of Learning to learn by gradient descent by gradient descent
MIT License
312 stars 54 forks source link

pytorch 0.3 correction #4

Closed Forbu closed 6 years ago

Forbu commented 6 years ago

The current version of the code produce a NxN matrix of weight instead of a N vector of weight (N the number of weight of the model to optimize). I modify a bit the code to produce the correct vector.