# Is there any replacement in Julia for ImageDataGenerator

**URL:** <https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785>\
**Category:** General Usage\
**Created:** [March 10, 2020, 5:42am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785 "2020-03-10T05:42:57Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![Eldho.Ashna](https://avatars.discourse-cdn.com/v4/letter/e/bc8723/32.png) [@Eldho.Ashna](https://discourse.julialang.org/u/Eldho.Ashna)\
**Post date:** [March 10, 2020, 5:42am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/1 "2020-03-10T05:42:57Z")

</div>

Hi,

I was trying to rewrite a python code of cat vs dog classification into julia. In the python code, I have the following:

```julia
from keras.preprocessing.image import ImageDataGenerator

# All images will be rescaled by 1./255
train = ImageDataGenerator(rescale=1./255)
test = ImageDataGenerator(rescale=1./255)

train_generator = train.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test.flow_from_directory(
        test_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary')

```

I tried converting this to Julia using : `using Keras: ImageDataGenerator`, it gave me error.  
So, I tried using PyCall. I did the following:

```julia
using PyCall
py"""
from keras.preprocessing.image import ImageDataGenerator
# All images will be rescaled by 1./255
train = ImageDataGenerator(rescale=1./255)
test = ImageDataGenerator(rescale=1./255)
train_generator = train.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test.flow_from_directory(
        test_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary')

"""

```

But, I’m getting the following error:

```julia
PyError ($(Expr(:escape, :(ccall(#= /home/g2-test/.julia/packages/PyCall/kAhnQ/src/pyeval.jl:38 =# @pysym(:PyEval_EvalCode), PyPtr, (PyPtr, PyPtr, PyPtr), o, globals, locals))))) <class 'NameError'>
NameError("name 'train_dir' is not defined")
  File "/home/g2-test/.julia/packages/PyCall/kAhnQ/src/pyeval.jl", line 7, in <module>
    pynamespace(m::Module) =

Stacktrace:
 [1] pyerr_check at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/exception.jl:60 [inlined]
 [2] pyerr_check at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/exception.jl:64 [inlined]
 [3] _handle_error(::String) at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/exception.jl:81
 [4] macro expansion at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/exception.jl:95 [inlined]
 [5] #120 at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/pyeval.jl:38 [inlined]
 [6] disable_sigint at ./c.jl:446 [inlined]
 [7] pyeval_(::String, ::PyDict{String,PyObject,true}, ::PyDict{String,PyObject,true}, ::Int64, ::String) at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/pyeval.jl:37
 [8] top-level scope at /home/g2-test/.julia/packages/PyCall/kAhnQ/src/pyeval.jl:230
 [9] top-level scope at In[50]:2

```

How can I solve this? Is there any other way?

---

<div class="post-metadata">

**Author:** ![jling](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jling/32/212909_2.png) [@jling](https://discourse.julialang.org/u/jling)\
**Post date:** [March 10, 2020, 6:06am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/2 "2020-03-10T06:06:23Z")

</div>

what is your `train_dir `

---

<div class="post-metadata">

**Author:** ![Eldho.Ashna](https://avatars.discourse-cdn.com/v4/letter/e/bc8723/32.png) [@Eldho.Ashna](https://discourse.julialang.org/u/Eldho.Ashna)\
**Post date:** [March 10, 2020, 6:39am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/3 "2020-03-10T06:39:36Z")

</div>

train\_dir has 2 folders of cats and dogs each containing of around 1500 images each.

---

<div class="post-metadata">

**Author:** ![jling](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jling/32/212909_2.png) [@jling](https://discourse.julialang.org/u/jling)\
**Post date:** [March 10, 2020, 7:11am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/4 "2020-03-10T07:11:28Z")

</div>

yea but you’re not defining it anywhere, are you?

---

<div class="post-metadata">

**Author:** ![Eldho.Ashna](https://avatars.discourse-cdn.com/v4/letter/e/bc8723/32.png) [@Eldho.Ashna](https://discourse.julialang.org/u/Eldho.Ashna)\
**Post date:** [March 10, 2020, 8:07am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/5 "2020-03-10T08:07:36Z")

</div>

Yes. I’m defining it.

```julia
train_dir = '/home/g2-test/ASHNA/classification/dog vs cat/dataset/training_set/'
classes = ['cat', 'dog']

```

---

<div class="post-metadata">

**Author:** ![jling](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jling/32/212909_2.png) [@jling](https://discourse.julialang.org/u/jling)\
**Post date:** [March 10, 2020, 8:09am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/6 "2020-03-10T08:09:48Z")

</div>

it’s not in the code you’re showing

---

<div class="post-metadata">

**Author:** ![Eldho.Ashna](https://avatars.discourse-cdn.com/v4/letter/e/bc8723/32.png) [@Eldho.Ashna](https://discourse.julialang.org/u/Eldho.Ashna)\
**Post date:** [March 10, 2020, 8:19am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/7 "2020-03-10T08:19:24Z")

</div>

This is the complete code:

```julia
using Flux
using Images
path = "/home/g2-test/ASHNA/classification/dog vs cat/dataset"
train_dir = "/home/g2-test/ASHNA/classification/dog vs cat/dataset/training_set/"
classes = ["cat", "dog"]
test_dir = "/home/g2-test/ASHNA/classification/dog vs cat/dataset/test_set/"
model = Chain(
              Conv((3, 3), (150 => 148), pad=(1,1), relu),
              MaxPool((2, 2)),
              Conv((3, 3), (74=>72), pad=(1, 1), relu),
              MaxPool((2, 2)),
              Conv((3, 3), (36=>34), pad=(1, 1), relu),
              MaxPool((2, 2)),
              Conv((3, 3), (17=>15), pad=(1, 1), relu),
              MaxPool((2, 2)),
              x -> reshape(x, :, size(x, 4)),
              Dense(6272, 512),
              Dense(512, 1),
              softmax)
using BSON: @save
@save "cat_vs_dog_model.bson" model
using PyCall
py"""
from keras.preprocessing.image import ImageDataGenerator
# All images will be rescaled by 1./255
train = ImageDataGenerator(rescale=1./255)
test = ImageDataGenerator(rescale=1./255)
train_generator = train.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test.flow_from_directory(
        test_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary')

"""

```

---

<div class="post-metadata">

**Author:** ![jling](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jling/32/212909_2.png) [@jling](https://discourse.julialang.org/u/jling)\
**Post date:** [March 10, 2020, 8:29am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/8 "2020-03-10T08:29:45Z")

</div>

whatever is in `py"""` you can think of running in a separate python REPL, so it won’t know about anything you write in Julia, try repeat those lines inside `py"""`

---

<div class="post-metadata">

**Author:** ![GunnarFarneback](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/gunnarfarneback/32/1827_2.png) [@GunnarFarneback](https://discourse.julialang.org/u/GunnarFarneback)\
**Post date:** [March 10, 2020, 8:45am UTC](https://discourse.julialang.org/t/is-there-any-replacement-in-julia-for-imagedatagenerator/35785/9 "2020-03-10T08:45:23Z")

</div>

> [@Eldho.Ashna](#):
>
> How can I solve this? Is there any other way?

Try

```julia
using PyCall
ImageDataGenerator = pyimport("keras").preprocessing.image.ImageDataGenerator
train = ImageDataGenerator(rescale = 1/255)
train_generator = train.flow_from_directory(train_dir, target_size = (150, 150), batch_size = 20, class_mode = "binary")

```

I have no idea how easily `train_generator` can be hooked up to Flux but at least you have it available on the Julia side of PyCall.