⬢github Python · 104.7K ★ +650 since we first saw it · pushed 8 min ago · NOASSERTION
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PyTorch is a Python library for tensor computation with strong GPU acceleration and dynamic neural networks built on tape-based automatic differentiation. It includes a NumPy-like tensor library, an autograd system, a neural network module, multiprocessing utilities, and data loaders. It can be used as a GPU-accelerated NumPy replacement or as a deep learning research platform with flexible, Python-first APIs.
Why now: not clear from the sources
Who it is for: Machine learning researchers, deep learning engineers, and scientists who want GPU-accelerated tensor math and flexible neural network development in Python.
autograddeep-learninggpumachine-learningneural-networknumpypythontensor
Stars over our 403 snapshots: 104K to 104.9K, since 4 d ago.
Where people talked about it
- ⬢github pytorch/pytorch 2 d ago
API: https://socialmediatrends-api.osmike.com/v1/repos/pytorch/pytorch