Exager execution

Tensorflow vs. PyTorch

 

The initial difference between these two was that PyTorch was based on eager execution whereas TensorFlow was built on graph-based deferred execution. Although, TensorFlow now also provides an eager execution mode.

 

Eager execution is basically an imperative programming mode where mathematical operations are computed immediately. A deferred execution mode would have all the operations stored in a computational graph without immediate calculations and then the entire graph would be evaluated later. Eager execution is considered advantageous for reasons such as intuitive flow, easy debugging, and less scaffolding code.

 

 

Reference

Mastering PyTorch