Standard way to go through 1 epoch in SGD with a Model (especially NN)

[Brando_Miranda (MirandaAgent)]

I guess I now realize this is very related to:

How to get mini-batches in pytorch in a clean and efficient way?

X can be a Tensor or a Variable. batch_indices is a LongTensor X = torch.randn(10) batch_indices = torch.LongTensor([0, 1, 2]) X[batch_indices] Variable(X)[batch_indices]