add adaptive pooling layers

[dnabanita7]

I have added AdaptiveMaxPool and AdaptiveMeanPool so that we can do a similar PyTorch implementation. cc @darsnack

PR

• Tests are added
• Entry in NEWS.md
• Documentation, if applicable
• Final review from @MikeInnes or @dhairyagandhi96 (for API changes).

Flux issue linking

Flux#1224

MLH issue linking

0.3.x-projects#26

[darsnack]

There are some test errors. Check the Travis log for more details.

[darsnack]

Looks like you have test errors with this line. You can look at the Travis build log for more details.

Can you fix this?

[darsnack]

Same comment.

[darsnack]

Can you fix the errors from the lines I commented originally? (Hint: you might need broadcasting)

[dnabanita7]

ok! actually I have been trying and not getting what is the error and also I can't do tests on my system because of the under lying MLH-Fellowship fork.

[darsnack]

No problem! insize and outsize are tuples, so you need to use broadcasting to divide them element-wise (e.g. insize ./ outsize). The other issue is that insize will have to extra elements for the channel and batching dimensions. So you want to drop the last two elements: insize[1:end-2].

[darsnack]

Similar issues with other arithmetic operations involving insize and outsize. You need to add broadcasting for all those cases too.

[darsnack]

Almost! The broadcasting thing applies to outsize - 1 as well. Tuples are annoying.

[dnabanita7]

Almost! The broadcasting thing applies to outsize - 1 as well. Tuples are annoying.

Yeah, I thought it to be my commit message.

So, the test AdaptiveMaxPool((4, 2))(x) == maxpool(2, PoolDims(2, 2)) is not correct for x = randn(Float32, 10, 10, 3, 2).

[darsnack]

Not sure what happened here with the bot. Yes, that test wouldn't be correct since going from (10, 10) -> (4, 2) means the stride is (2.5, 5). So to get it to work, you would need to add padding.

[dnabanita7]

yeah, I am switching back to (10,10) -> (5,5) which would clear all the doubts