Agreed. I used TensorFlow 1.x before PyTorch matured. Today, all of my deep lear...

osipov on July 17, 2020 | parent | context | favorite | on: TensorFlow, Keras and deep learning, without a PhD

Agreed. I used TensorFlow 1.x before PyTorch matured. Today, all of my deep learning is PyTorch based because TensorFlow 2.x didn't fix the core TensorFlow 1.x issues (e.g., poor reproducibility, unintuitive API design) and PyTorch performs better than Keras w/TensorFlow backend.