PyTorch vs. TensorFlow: 1 month summary

> A forward() function gets called when the Graph is run.

Isn't that almost exactly the same in tensorflow? You'd run your model to generate an output, or/and run your optimization operation t optimize the model.

> Based on some reviews, PyTorch also shows a better performance on a lot of models compared to TensorFlow.

Citation needed. How good are the examples optimized? What does performance mean? Precision or learning iterations per second?

If it's the later, in which environment? CPU/GPU/distributed computing?

While I think that this is a somewhat useful rough overview, it should have had some more details about the actual differences and in particular how to accomplish the same thing with some code examples in each library.

On a side note: I know that I can also link tensorflow directly to a C++ application instead of using it with python. Can the same be done with pytorch?