TensorFlow 1 vs TensorFlow 2: Is the new TF better?

TensorFlow is no longer what it used to be.

Let’s have a quick history of development overview:
TensorFlow 1 is one of the most widely used deep learning packages. It is very versatile and that is why many practitioners like it. However, it has a major disadvantage – it is very hard to learn and use.

This led to the development and popularization of higher-level packages such as PyTorch and Keras. Keras is especially interesting as in 2017 it was integrated in the core TensorFlow – a feat that may sound a bit strange. In reality though, both TensorFlow and Keras are open source, so such things do happen in the programming world. In fact, Keras’ author claims that Keras is conceived as “an interface for TensorFlow rather than a different library”, making this integration even easier to digest and implement.

However, even with Keras as a part of TF, TensorFlow was still losing popularity.
This was addressed in 2019, when TensorFlow 2.0 came on the horizon. It is TensorFlow’s effort to catch up with the current demand for higher-level programming. Interestingly, instead of creating their own high-level syntax, the TF developers chose to borrow that of Keras. This decision made sense as Keras was widely adopted already and people generally love it. On that note, you may hear people saying: TensorFlow 2 is basically Keras.

In fact, TF 2 has the best of both worlds – most of the versatility of TF 1 and the high-level simplicity of Keras.

And that’s not all. There are also other major advantages of TF 2 over TF 1.

So, if you want to learn more about the advantages of TF 2, make sure to watch the whole video!

365 Data Science is an online educational career website that offers the incredible opportunity to find your way into the data science world no matter your previous knowledge and experience. We have prepared numerous courses that suit the needs of aspiring BI analysts, Data analysts and Data scientists.

We at 365 Data Science are committed educators who believe that curiosity should not be hindered by inability to access good learning resources. This is why we focus all our efforts on creating high-quality educational content which anyone can access online.

#TensorFlow #statistics #tutorial

[wolfisraging]

I really had no problem with tf 1.x, it was great. While tf 2.0 is extremely confusing, even the available codes for tf 2.0 on their official website give errors.
I hope tf 2.0 would become mature as soon as possible.

[nikosellinas]

Lol, PyTorch isn't a higher level package. Keras is.

[SimonaDobreva]

awesome thank s, feels like this is the only review like this !

[princeofexcess]

Alright but eager execution should come at a performance loss. What is the performance loss from removing graphs and why is it so hard to find any data on this.

[mhh]

This channel is so underrated. Subscribed

[vivekbhujbal]

anybody using tensorflow 2.3 with google collab please comment.

[rs-tarxvfz]

I think TF1 was a big *Technical Debt* left behind.

[FerrisMcLaren]

Who cares which is better. The real question is who the fuck has gotten it to work in late 2019?! No tutorials and waaaay to hard to install. Needs fixing