Deep Learning Frameworks Compared

Share it with your friends Like

Thanks! Share it with your friends!


In this video, I compare 5 of the most popular deep learning frameworks (SciKit Learn, TensorFlow, Theano, Keras, and Caffe). We go through the pros and cons of each, as well as some code samples, eventually coming to a definitive conclusion.

The code for the TensorFlow vs Theano part of the video is here:

An article that explains the differences in more detail:

I created a Slack channel for us, sign up here:

Learn more about TF Learn here:

and here:

Learn more about TensorFlow here:

More on Keras here:

More on SciKit Learn here:

More on Caffe here:

More on Theano here:

Thanks for watching guys, I do this for you. If you like my videos, feel free to support me on Patreon and please LIKE, SUBSCRIBE, COMMENT, AND SHARE!
Follow me:
Facebook: Instagram: Instagram:
Signup for my newsletter for exciting updates in the field of AI:
Hit the Join button above to sign up to become a member of my channel for access to exclusive content!


Sachin Jha says:

2:32 line 9 error

Abhijit Bandyopadhyay says:

What about MS CNTK?

António Caeiro says:

I would love to see an update video in 2019

saurabh pandey says:

Pytorch anyone?

Vatsalay Khobragade says:

i feel verry bad for scikit learn 🙁

Cory Cook says:

Is it just me or does the Airbnb icon look like a erect penis

Salah Eddine Ghamri says:

You don't know pytorch ?


what will you say about caffe2 and pytorch as compared to all these frameworks?

Minting Coins says:

If it makes sense, could you make an updated version of this video?

Atharva Pagare says:

Guess who has windows support now? 🙂

Daniel Baron says:

Informative video, I would have to disagree with the end statement that Tensorflow is best for research. I would absolutely recommend that anyone looking to perform research, or simply learn how to create Neural Network based models, they should look at Pytorch. It doesn't depend on graph computation which makes it far easier to debug. The cost in performance for a non graph based deep learning library has been blown out of proportion by Tensorflow fans IMO.

Visalini Kumaraswamy says:

You have content.. but, be a bit slow.. Why are you rushing.. 0.25% slower than as it is now would do much better… Content Delivery is really important..

Deep Learning Partnership says:

Theano dead.

chris mahn says:

hmm airbnb logo looks like an erect ** lol

Sayyam Jain says:

2 Minutes silence for Theano

ChegevaraXR650R says:


Prateek Gupta says:

Hehehehe.. "how many layers you got?". Would rather it more if he were like "Are O sambha..Kitni layers h?"

Anshuman Kumar says:

Mx net master race

Wasi Ali says:

can we use tensorflow with java?

Nikunj sardhara says:

Who else noticed ac tivation?

cuong tran says:

hi. Can you use neural networks to compare two texts? If feasible, hopefully you can provide me with documentation and explanation. thank you. thank you very much

Faiga Alawad says:

What about caffe2 ?

Joey Ortiz says:

0:15 is that really AirBnb's Logo? ….

Hammerhead Monkey says:

Those memes are hilarious!

Write a comment