I built the same model with TensorFlow and PyTorch | Which Framework is better?

I created the same model with TensorFlow and PyTorch. Which Deep Learning Framework is better? TensorFlow vs. PyTorch!

Get my Free NumPy Handbook:

📓 ML Notebooks available on Patreon:

If you enjoyed this video, please subscribe to the channel:

~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~

~~~~~~~~~~~~~~ SUPPORT ME ~~~~~~~~~~~~~~

#Python #deeplearning

Timeline:
00:00 - Introduction
01:47 - TensorFlow
06:10 - PyTorch

----------------------------------------------------------------------------------------------------------
* This is a sponsored link. By clicking on it you will not have any additional costs, instead you will support me and my project. Thank you so much for the support! 🙏

[lukewood]

Not using a validation split is actually a pretty big difference. For some additional perspective, adding additional training examples is typically more beneficial than model architecture differences. You shouldn't use the split in TensorFlow if you want to make a comparison like this; even if you cite this reason.

[DHAtEnclaveForensics]

The results are also different because the initialization of the weights and biases is random. Unless you make them identical you can never expect to get the same results.

[cristianpadurariu]

what about weight initialization? .... that could affect the performance pretty dramatically in some cases

[ai_minds_]

If you used all data for train torch model, there is no point to compare metrics
+ you should define random seed as well

[maxxel_]

great vid, was cool for me to see how initializing and training a model in pytorch looks like

[prathameshdinkar]

Nice video! Just want to add at 2:09, there are 3 methods to create the tf model. I think you missed to mention functional API which is intermediate between Sequential and Subclassing

[wyctorfogos]

Great video ! But only one observation: you must compare the models'creation using the Tensorflow in it's Advanced mode, because Pytorch ia based on Oriented object.

[ogrp]

Saying that PyTorch is better than TF by just looking at the results of one run? Deep learning models have a random component … so this result is completely lead by chance. When I see the title of the video, I thought the video was about doing a real comparison regarding usability, memory and GPU consumption, etc

[RohanPaul-AI]

Nice and clean presentation in 13 mints. Great video, Thank you.

[bediosoro]

I think that you should have use model sequential in pytorch or use gratienttape approach in tensorflow for better comparison.

[shivamroy]

Very informative and crisp video. Love the effort put into it. Keep up the good work !

[StaMariaRock]

As a begginner, Tensorflow feels way easier, pytorch looks and feels like some deep engineering, I guess I might have to learn both. But I still prefer Tensorflow, feels like it available for everyone

[juanete]

Can I use "crossentropy" as a metric as we also do for the loss?

[md.arrahmandip]

Hello there, how to setup both pytorch and tensorflow in same machine using one cuda toolkit? Or in different environment maintaining same cuda toolkit?
Thank you.

[robcecchini]

A YouTube comment section with well thought out intelligent comments, making valid arguments in favor and opposition! 🤯 Great input worth pondering!

[parttimelarry]

Great video and editing, you covered a lot of ground in 13 minutes.

[davidtindell]

Good overview. TU.
I employ both frameworks and often prototype on Apple Silicon as well as
Intel ++ NVidea ...
. . .

[monisprabu]

Thank you very much for this comparison !!!

[paul_devos]

Wow. Great video doing the side by side. Momentum and adoption seems to favor PyTorch and in general, many FB frameworks over Google frameworks. I could definitely see where if you're a very good Python developer (or want to be), PyTorch would be a very "easy" choice. TensorFlow seems very easy for the "incremental" command workflows that many Data Scientists do especially if they aren't really good with OOP.

So in essence, TensorFlow feels a little bit like R for Stats, a "researcher first" tool... you get a ton of stuff just included, whereas with Python, you have to build and customize all your outputs, which feels more SWE driven than Researcher/Academic driven, e.g. like R.

[cloud_]

What about training and evaluation time? Which has less value?