# How to correctly handle batches in this model

**URL:** <https://discourse.julialang.org/t/how-to-correctly-handle-batches-in-this-model/26570>\
**Category:** Machine Learning\
**Created:** [July 20, 2019, 12:03am UTC](https://discourse.julialang.org/t/how-to-correctly-handle-batches-in-this-model/26570 "2019-07-20T00:03:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![danipozo](https://avatars.discourse-cdn.com/v4/letter/d/f4b2a3/32.png) [@danipozo](https://discourse.julialang.org/u/danipozo)\
**Post date:** [July 20, 2019, 12:03am UTC](https://discourse.julialang.org/t/how-to-correctly-handle-batches-in-this-model/26570/1 "2019-07-20T00:03:09Z")

</div>

I’m trying to write a model similar to the one in [Image to markup with coarse to fine attention](https://arxiv.org/abs/1609.04938v2), where a fully convolutional network is first applied to an image (resulting in a smaller image with a greater number of channels, e.g., shape (80,80,256)), and then a bidirectional LSTM is applied to **each row** of the resulting image.

I don’t know how to correctly handle batches since this seems to require that I write some explicit iteration, accessing the rows in a non shape-independent way:

```julia
function (m::RowEncoder)(x)
    out = zeros(m.rows, m.columns, m.features)
    for i in 1:m.rows
        out[i, :, :] = m.bidir_lstm(x[i, :, :])
        Flux.reset!(m.bidir_lstm)
    end
end

```

but this errors when called on a batch with shape `(rows,colums,features,examples)`. Can I write a specific version of the function for each shape? Do I need to do this? Or is there a way to write a shape-generic function that also handles BiLSTM resets?

Thanks,  
Daniel