# Communicating julia and python for deep learning

**URL:** <https://discourse.julialang.org/t/communicating-julia-and-python-for-deep-learning/35510>\
**Category:** General Usage\
**Created:** [March 4, 2020, 10:41am UTC](https://discourse.julialang.org/t/communicating-julia-and-python-for-deep-learning/35510 "2020-03-04T10:41:13Z")\
**Posts on this page:** 2\
**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 4, 2020, 10:41am UTC](https://discourse.julialang.org/t/communicating-julia-and-python-for-deep-learning/35510/1 "2020-03-04T10:41:13Z")

</div>

Hi all,

I was learning to make normal python code communicate with julia. But, I don’t know how this will happen for deep learning. For example, `opencv` in python can be communicated with julia using

```julia
using PyCall
cv2 = pyimport("cv2")

```

Similarly, how can keras and tensorflow be communicated with julia?  
Also, I had done a binary classification using python. Can this weight file be accessed using julia? If yes, how?

---

<div class="post-metadata">

**Author:** ![carstenbauer](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/carstenbauer/32/4981_2.png) [@carstenbauer](https://discourse.julialang.org/u/carstenbauer)\
**Post date:** [March 4, 2020, 12:13pm UTC](https://discourse.julialang.org/t/communicating-julia-and-python-for-deep-learning/35510/2 "2020-03-04T12:13:37Z")

</div>

`tf = pyimport("tensorflow")`? Note that there is also [TensorFlow.jl](https://github.com/malmaud/TensorFlow.jl).

As this isn’t your first post on Julia-Python interop within the last few days, I really recommend you read the [PyCall.jl](https://github.com/JuliaPy/PyCall.jl) README to understand the interface better.