# Julia/Flux creating a model correctly - using Chain Embedding layer reshaping & Dense layers

**URL:** <https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089>\
**Category:** Machine Learning\
**Tags:** question, embedding, flux\
**Created:** [February 5, 2023, 12:01pm UTC](https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089 "2023-02-05T12:01:08Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![roeya](https://avatars.discourse-cdn.com/v4/letter/r/ecb155/32.png) [@roeya](https://discourse.julialang.org/u/roeya)\
**Post date:** [February 5, 2023, 12:01pm UTC](https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089/1 "2023-02-05T12:01:08Z")

</div>

I am trying to follow an old article about word embedding in Julia language with Flux: [Julia Word Embedding Layer in Flux - Self Trained - Getting to Know Julia](https://spcman.github.io/getting-to-know-julia/deep-learning/nlp/flux-embeddings-tutorial-1/)

As it is an old outdated article I managed to handle the embedding layer correctly using the new embedding layer of Flux (0.13.11). The Chain looks like this:

```julia
embedding = Flux.Embedding(vocab_size => max_features, init=Flux.glorot_normal)
model = Chain(embedding(Flux.onehotbatch(reshape(x, pad_size*N), 0:vocab_size-1)),
           x -> reshape(x, max_features, pad_size, N),
           x -> mean(x, dims=2),
           x -> reshape(x, 8, 10),
           Dense(8, 1),
)

```

When I try to check the model my calling model(x) I get: ERROR: MethodError: objects of type Matrix{Float32} are not callable Use square brackets for indexing an Array.

My guess that the problem somehow connected to the reshaping. I am new to both Julia & Flux so sorry if the question is basic.

Any clue what should I do?

---

<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:** [February 6, 2023, 12:18am UTC](https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089/2 "2023-02-06T00:18:48Z")

</div>

This is one of those cases where looking at the full stacktrace and not just the error message helps. `embedding` is a callable struct which represents an embedding layer. Instead of passing this layer object to `Chain` like the tutorial does, you’re passing the output from calling it on some arbitrary input. Said output is a Matrix, so when `Chain` goes to call what it thinks is an `Embedding` layer it ends up invoking `output_matrix_from_embedding(x)` and predictably fails.

If you’re familiar with how layers work in other ML frameworks, Flux layers work much the same.

---

<div class="post-metadata">

**Author:** ![roeya](https://avatars.discourse-cdn.com/v4/letter/r/ecb155/32.png) [@roeya](https://discourse.julialang.org/u/roeya)\
**Post date:** [February 6, 2023, 7:25am UTC](https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089/3 "2023-02-06T07:25:38Z")

</div>

Ok - As I am new to both Julia, Flux & Deep Learning I understand that something basic was wrong.  
Should I just input the transposed document term index as input to the embedding layer? - how will it be hot encoded? I am clearly missing something…

---

<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:** [February 7, 2023, 1:05am UTC](https://discourse.julialang.org/t/julia-flux-creating-a-model-correctly-using-chain-embedding-layer-reshaping-dense-layers/94089/4 "2023-02-07T01:05:52Z")

</div>

Very little has to change. Just make sure what you’re passing to `Chain` are actual layers:

```julia
model = Chain(
  embedding,
  x -> reshape(x, max_features, pad_size, N),
  x -> mean(x, dims=2),
  x -> reshape(x, 8, 10),
  Dense(8, 1),
)

```

And then you can call your model with whatever you want:

```julia
x = Flux.onehotbatch(reshape(x, pad_size*N), 0:vocab_size-1)
model(x)

```

This I believe should match the behaviour in the linked article.