# Batch time-series input for RNN

**URL:** <https://discourse.julialang.org/t/batch-time-series-input-for-rnn/59469>\
**Category:** Machine Learning\
**Tags:** array, time-series\
**Created:** [April 17, 2021, 10:05am UTC](https://discourse.julialang.org/t/batch-time-series-input-for-rnn/59469 "2021-04-17T10:05:14Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sunny](https://avatars.discourse-cdn.com/v4/letter/s/7c8e57/32.png) [@Sunny](https://discourse.julialang.org/u/Sunny)\
**Post date:** [April 17, 2021, 10:05am UTC](https://discourse.julialang.org/t/batch-time-series-input-for-rnn/59469/1 "2021-04-17T10:05:14Z")

</div>

How to form and feed a proper batch to feed to RNN?  
It is possible to apply RNN to batch of one data point time-series inputs:

```julia
# single sample
rnn = RNN(2,3)
seq = ones(Float32,(2,10)) 
rnn(seq) # apply to 10 sample independently

# Output:
3×10 Array{Float32,2}:
 -0.342626 -0.342626 -0.342626 … -0.342626 -0.342626 -0.342626
 -0.56927 -0.56927 -0.56927 -0.56927 -0.56927 -0.56927
 -0.688904 -0.688904 -0.688904 -0.688904 -0.688904 -0.688904 

```

Also I know how to apply it to single sequence of data

```julia
# Time series of length 5
seq = [rand(Float32,2) for i=1:5]
rnn.(seq) # apply to single sequence 
Output:
5-element Array{Array{Float32,1},1}:
 [-0.7071419, 0.7136748, 0.478005]
 [-0.697015, 0.9357477, -0.79483825]
 [-0.77859926, 0.88962847, 0.55188143]
 [-0.7391649, 0.9885068, -0.6310922]
 [-0.76783645, 0.89206576, 0.26163444]

```

There is a way to get the batch of time series:

```julia
seq = [rand(Float32,(2,10)) for i=1:5]
rnn.(seq) # apply to 10 sequences independently

#Output: 

5-element Array{Array{Float32,2},1}:
 [-0.88525283 -0.69476825 … -0.89752537 -0.89838624; 0.9713873 0.9787338 … 0.9860863 0.9857219; -0.7818201 -0.367579 … -0.6444337 -0.6539876]
 [-0.91649914 -0.6018399 … -0.8816908 -0.88034606; 0.78649575 0.9152232 … 0.90690774 0.8112091; -0.250717 0.18231556 … 0.053293146 -0.27068266]
 [-0.8498657 -0.8136713 … -0.9134936 -0.91809046; 0.8846819 0.9200575 … 0.9767982 0.9774641; -0.37103912 -0.83741844 … -0.5929827 0.082197964]
 [-0.69060314 -0.8576724 … -0.7624638 -0.77607745; 0.95665026 0.75602245 … 0.95435596 0.9842143; 0.4997346 0.11458533 … 0.5946678 -0.15885094]
 [-0.43952018 -0.8901464 … -0.7802511 -0.51005286; 0.9877861 0.98162913 … 0.9833198 0.8864663; -0.32135123 -0.3325736 … -0.8334724 -0.22399448]

```

But for my problem I want to use `Flux.Data.Dataloader` for a dataset with numerous time-series data.  
My input has 3 dimensions, and the last one should be the `batch_size` in order to apply `Dataloader`. In contrast `[rand(Float32,(2,10)) for i=1:5]` has size (5,).  
The question is how to construct a dataset that the `Dataloader` and `RNN` can be applied to some batch?

---

<div class="post-metadata">

**Author:** ![ToucheSir](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/touchesir/32/14411_2.png) [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)\
**Post date:** [April 17, 2021, 8:07pm UTC](https://discourse.julialang.org/t/batch-time-series-input-for-rnn/59469/2 "2021-04-17T20:07:49Z")

</div>

AFAIK Flux’s DataLoader does not do any collation for non-array inputs, so you’d have to handle that yourself before passing the data off to the RNN. If you don’t mind the extra dependency, [https://github.com/lorenzoh/DataLoaders.jl](https://github.com/lorenzoh/DataLoaders.jl) _does_ handle this in a fashion similar to what you’d expect from PyTorch’s DataLoader.