Brancher vs SciPy: What are the differences?

Developers describe Brancher as "A Python package for differentiable probabilistic inference". It is a user-centered Python package for differentiable probabilistic inference. It allows to design and train differentiable Bayesian models using stochastic variational inference. It is based on the deep learning framework PyTorch. On the other hand, SciPy is detailed as "Scientific Computing Tools for Python". Python-based ecosystem of open-source software for mathematics, science, and engineering. It contains modules for optimization, linear algebra, integration, interpolation, special functions, FFT, signal and image processing, ODE solvers and other tasks common in science and engineering.

Brancher and SciPy belong to "Data Science Tools" category of the tech stack.

Brancher and SciPy are both open source tools. It seems that SciPy with 6.13K GitHub stars and 2.9K forks on GitHub has more adoption than Brancher with 163 GitHub stars and 29 GitHub forks.