Why Choose PyTorch Over TensorFlow or Scikit-learn?

[MartyAckerman]

One great thing about scikit is the infrastructure around data pipelines and transformations. You can use the skorch library to wrap your PyTorch model so that it works in a scikit pipeline.

[OnLyhereAlone]

Having finetuned a couple of BERT models before being familiar with Pytorch and Tensorflow, as a newbie, I wondered what their purposes were as their syntaxes seem similar to SKLearn. The proverbial light bulb came up in my head the moment you said SKL is for standard machine learning while these other libraries are for deep learning / neural networks. I realized I've had this thought before but their video helped confirm it.
Thank you.

[landryplacid]

Sklearn is a basic library. Tensorflow and pytorch are the used for deep and reinforcement learning.