# Batching in Flux 0.11.1

**URL:** <https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105>\
**Category:** Machine Learning\
**Created:** [June 17, 2021, 5:31pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105 "2021-06-17T17:31:48Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![sapo](https://avatars.discourse-cdn.com/v4/letter/s/ec9cab/32.png) [@sapo](https://discourse.julialang.org/u/sapo)\
**Post date:** [June 17, 2021, 5:31pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/1 "2021-06-17T17:31:49Z")

</div>

Hello,  
for a dependency issue, I have to use Flux at version 0.11.1.

I cannot understand how to use batches:

```julia
julia> using Flux

julia> d = Dense(5, 2)
Dense(5, 2)

julia> d(rand(Float32, 5, 64)) |> size
(2, 64)

julia> d(rand(Float32, 5, 1, 64)) |> size
ERROR: MethodError: no method matching *(::Array{Float32,2}, ::Array{Float32,3})
Closest candidates are:
  *(::Any, ::Any, ::Any, ::Any...) at operators.jl:529
  *(::ChainRulesCore.NotImplemented, ::Any) at /home/sapo/.julia/packages/ChainRulesCore/qbmEe/src/d
ifferential_arithmetic.jl:27
  *(::ChainRulesCore.ZeroTangent, ::Any) at /home/sapo/.julia/packages/ChainRulesCore/qbmEe/src/diff
erential_arithmetic.jl:120
  ...
Stacktrace:
 [1] (::Dense{typeof(identity),Array{Float32,2},Array{Float32,1}})(::Array{Float32,3}) at /home/sapo
/.julia/packages/Flux/05b38/src/layers/basic.jl:123
 [2] (::Dense{typeof(identity),Array{Float32,2},Array{Float32,1}})(::Array{Float32,3}) at /home/sapo
/.julia/packages/Flux/05b38/src/layers/basic.jl:134
 [3] top-level scope at REPL[27]:1
 [4] eval(::Module, ::Any) at ./boot.jl:330
 [5] eval_user_input(::Any, ::REPL.REPLBackend) at /buildworker/worker/package_linux64/build/usr/sha
re/julia/stdlib/v1.3/REPL/src/REPL.jl:86
 [6] run_backend(::REPL.REPLBackend) at /home/sapo/.julia/packages/Revise/1boD5/src/packagedef.jl:12
21
 [7] top-level scope at REPL[1]:0

```

---

<div class="post-metadata">

**Author:** ![darsnack](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/darsnack/32/10144_2.png) [@darsnack](https://discourse.julialang.org/u/darsnack)\
**Post date:** [June 17, 2021, 6:37pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/2 "2021-06-17T18:37:14Z")

</div>

I’m not sure I see the connection to batching. What were you intending `rand(Float32, 5, 1, 64)` to signify? 64 samples with a batch size of 1?

---

<div class="post-metadata">

**Author:** ![sapo](https://avatars.discourse-cdn.com/v4/letter/s/ec9cab/32.png) [@sapo](https://discourse.julialang.org/u/sapo)\
**Post date:** [June 17, 2021, 6:54pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/3 "2021-06-17T18:54:26Z")

</div>

1 batch with 5 samples and 64 features

---

<div class="post-metadata">

**Author:** ![sapo](https://avatars.discourse-cdn.com/v4/letter/s/ec9cab/32.png) [@sapo](https://discourse.julialang.org/u/sapo)\
**Post date:** [June 17, 2021, 7:02pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/4 "2021-06-17T19:02:25Z")

</div>

From the slack channel: this feature was added in Flux 0.12 with [this](https://github.com/FluxML/Flux.jl/pull/1405) PR.

It’s not compatible with Julia 1.3.1 though, any idea about how to solve this issue? I need to stay on Julia 1.3.1 for now because of Cxx.

```julia
(nmf) pkg> add Flux@0.12.4
 Resolving package versions...
ERROR: Unsatisfiable requirements detected for package CUDA [052768ef]:
 CUDA [052768ef] log:
 ├─possible versions are: [0.1.0, 1.0.0-1.0.2, 1.1.0, 1.2.0-1.2.1, 1.3.0-1.3.3, 2.0.0-2.0.2, 2.1.0, 2.2.0-2.2.1, 2.3.0, 2.4.0-2.4.3, 2.5.0, 2.6.0-2.6.3, 3.0.0-3.0.3, 3.1.0, 3.2.0-3.2.1, 3.3.0] or uninstalled
 ├─restricted by compatibility requirements with Flux [587475ba] to versions: [3.0.0-3.0.3, 3.1.0, 3.2.0-3.2.1, 3.3.0]
 │ └─Flux [587475ba] log:
 │ ├─possible versions are: [0.4.1, 0.5.0-0.5.4, 0.6.0-0.6.10, 0.7.0-0.7.3, 0.8.0-0.8.3, 0.9.0, 0.10.0-0.10.4, 0.11.0-0.11.6, 0.12.0-0.12.4] or uninstalled
 │ └─restricted to versions 0.12.4 by an explicit requirement, leaving only versions 0.12.4
 └─restricted by julia compatibility requirements to versions: [0.1.0, 1.0.0-1.0.2, 1.3.0-1.3.3] or uninstalled — no versions left

```

---

<div class="post-metadata">

**Author:** ![darsnack](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/darsnack/32/10144_2.png) [@darsnack](https://discourse.julialang.org/u/darsnack)\
**Post date:** [June 17, 2021, 7:06pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/5 "2021-06-17T19:06:39Z")

</div>

In Flux, the batch size is last. So, for image data, it follows WHCN format. Also, you only call the model on a batch at a time. So, `d(x)` assume that `x` is a batch of data. If you want one batch of five samples and 64 features, then you need

```julia
d = Dense(64, 2)
# apply to a single batch of size 5 w/ 64 features
d(rand(Float32, 64, 5))

# create a vector of 10 batches
# each batch is size 5 w/ 64 features
xs = [rand(Float32, 64, 5) for _ in 1:10]

# loop over the batches and apply the model
ys = []
for x in xs
  y = d(x)
  push!(ys, y)
end

# use map instead of a loop
ys = map(d, xs)

# use broadcasting
ys = d.(x)

```

Also, maybe you already have data that you need to split into batches. You can use the following:

```julia
using Iterators: partition

# create a 100 samples w/ 64 features each
X = rand(Float32, 64, 100)

# split into batches of size 5
xs = [X[:, i] for i in partition(1:100, 5)]

```

Lastly, the methods above are using basic Julia functionality which is usually sufficient for simple arrays of data like `X`. But for complex datasets, you might want to use data loaders with built-in batching like [`Flux.DataLoader`](https://fluxml.ai/Flux.jl/stable/data/dataloader/) or [`DataLoaders.DataLoader`](https://juliahub.com/ui/Packages/DataLoaders/KH1To/0.1.2).

---

<div class="post-metadata">

**Author:** ![darsnack](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/darsnack/32/10144_2.png) [@darsnack](https://discourse.julialang.org/u/darsnack)\
**Post date:** [June 17, 2021, 7:07pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/6 "2021-06-17T19:07:22Z")

</div>

Yeah if you need to stay on Julia 1.3.1 then you won’t be able to use Flux 0.12. Not much you can do.

---

<div class="post-metadata">

**Author:** ![sapo](https://avatars.discourse-cdn.com/v4/letter/s/ec9cab/32.png) [@sapo](https://discourse.julialang.org/u/sapo)\
**Post date:** [June 18, 2021, 8:58am UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/7 "2021-06-18T08:58:39Z")

</div>

Basically, what I need is to overload this function with this new version (taken from version 0.12):

```julia
function (a::Dense)(x::AbstractArray)
    W, b, σ = a.W, a.b, a.σ
    σ.(W*x .+ b)
    # reshape to handle dims > 1 as batch dimensions
    sz = size(x)
    x = reshape(x, sz[1], :) 
    x = σ.(W*x .+ b)
    return reshape(x, :, sz[2:end]...)
end

```

How can I do it? In my tests, Julia still prefers the Flux function, not mine

---

<div class="post-metadata">

**Author:** ![darsnack](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/darsnack/32/10144_2.png) [@darsnack](https://discourse.julialang.org/u/darsnack)\
**Post date:** [June 18, 2021, 1:04pm UTC](https://discourse.julialang.org/t/batching-in-flux-0-11-1/63105/8 "2021-06-18T13:04:28Z")

</div>

You need to either add `import Flux: Dense` at the start of your code. Or do `(a::Flux.Dense)(x::AbstractArray)` in your definition. (you need to override/extend the function in the `Flux` namespace).

Also, adding that override would make your code run, but I don’t think it will do want you want it to. Maybe I just misunderstood your explanation from before though.