# Performance using Resnets, googlenet, alexnet on Julia vs Python \[ Both when training time and testing time\]?
**URL:** https://discourse.julialang.org/t/performance-using-resnets-googlenet-alexnet-on-julia-vs-python-both-when-training-time-and-testing-time/51998
**Category:** Offtopic
**Tags:** question
**Created:** [December 17, 2020, 5:15pm UTC](https://discourse.julialang.org/t/performance-using-resnets-googlenet-alexnet-on-julia-vs-python-both-when-training-time-and-testing-time/51998 "2020-12-17T17:15:40Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@vedasulo](https://discourse.julialang.org/u/vedasulo)
#### Post date: [December 17, 2020, 5:15pm UTC](https://discourse.julialang.org/t/performance-using-resnets-googlenet-alexnet-on-julia-vs-python-both-when-training-time-and-testing-time/51998/1 "2020-12-17T17:15:40Z")
I am curious, about
_How much time did it take to train and also on testing for both Julia and Python languages_.
In networks such as googlenet, resnets, or Stylegan . ๐
Thank you for your answer.
Excited to see results as a motivation. ๐
---
### Author:  [@dmolina](https://discourse.julialang.org/u/dmolina)
#### Post date: [December 17, 2020, 5:38pm UTC](https://discourse.julialang.org/t/performance-using-resnets-googlenet-alexnet-on-julia-vs-python-both-when-training-time-and-testing-time/51998/2 "2020-12-17T17:38:59Z")
It is an interesting question.
A small benchmark information there are in [https://github.com/dfdx/Avalon.jl](https://github.com/dfdx/Avalon.jl) and [Introduction to Knet ยท Knet.jl](http://denizyuret.github.io/Knet.jl/latest/tutorial/#Benchmarks-1)
but with not so complex networks.
However, taking in account the performance of PyTorch and TensorFlow (and how much its code is actually in C++) I would guess that it is going to be worse than these famous frameworks.
Anyway, if any one have times/comparison, it should be always interesting to see it.
---
### Author:  [@vedasulo](https://discourse.julialang.org/u/vedasulo)
#### Post date: [December 18, 2020, 1:27pm UTC](https://discourse.julialang.org/t/performance-using-resnets-googlenet-alexnet-on-julia-vs-python-both-when-training-time-and-testing-time/51998/3 "2020-12-18T13:27:07Z")
They are pretty much same speed. Although pytorch or tensorflow bounded by c++ so they are fast.
But **why people are not adopting julia (fast and easy) instead of these frameworks**??? ๐
I was searching for Pytorch.jl (official) mainted by official community.
I had heard facebook converting php to Julia.
I hope facebook will also switch from pytorch python to pytorch julia. And it will be easy for us. ๐