Added more pooling layers to torch_nn.py

[suzgunmirac]

trafficstars

I realized that six of the pooling layers in torch.nn were initially missing, so I added them to torch_nn.py.

[srush]

Looks great, but lint tests are failing. Be sure to run format.sh first.

[srush]

Also be careful. MaxUnpool needs to indices, so it is not going to work.

input: the input Tensor to invert
indices: the indices given out by MaxPool3d

[srush]

Changed around the nn style a bit. maybe we can update avg pool to the new style.

(honestly though we won't use any of these this assignment, they're more for images)

[suzgunmirac]

Thank you so much for the update, Professor Rush! In this case, I will update the pooling layers once we finalize the nn style.