Compared to TF, PyTorch is extremely clean, unified, and well-documented. No duplicate functions with slightly different semantics. No deprecation warnings all over the code. A single way to do things instead of 10 different competing approaches. It feels great. Productive.
— Denny Britz (@dennybritz) January 30, 2019
PyTorch code turned out to be more concise and readable. PyTorch implementations were on average much shorter, and look more intuitive to someone not familiar with graph-based programming.
— Denny Britz (@dennybritz) January 30, 2019
Visualization. There are a few open source projects to visualize graphs, but none worked great. I'd really like a way to visualize a graph at multiple customized "levels" (ops, modules, module groups, etc). In TF this was easily possible with name scopes + Tensorboard.
— Denny Britz (@dennybritz) January 30, 2019
