[mlpack-git] [mlpack/mlpack] Inception layer (#757)

[Nilay Jain]

> +    // Forward pass for 3x3 pool path. 
> +    pool3.InputParameter() = input;
> +    pool3.Forward(input, pool3.OutputParameter());
> +    Pad(pool3.OutputParameter(), 1, 1, convPool.InputParameter());
> +    convPool.Forward(pool3.OutputParameter(), convPool.OutputParameter());
> +    biasPool.Forward(convPool.OutputParameter(), biasPool.OutputParameter());
> +    basePool.InputParameter() = biasPool.OutputParameter();
> +    basePool.Forward(convPool.OutputParameter(), basePool.OutputParameter());
> +
> +    // concatenate outputs of all the paths.
> +    output = arma::join_slices( 
> +              arma::join_slices(
> +                arma::join_slices( 
> +                  base1.OutputParameter(), base3.OutputParameter() ), 
> +                  base5.OutputParameter() ), basePool.OutputParameter());
> +

but inception layer does not do any operation in itself, it just calls its constituent layers, so if inception layer does not need to have any weights, what should we initialize it to?

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/757/files/06d923321f246f2c6ead9ad56e99309fe24a6f5c#r75575591
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160820/789671c7/attachment-0001.html>