Pytorch 基础

Pytorch with CUDA-aware MPI backend for distributed training

Implementation of Fast Transformer in Pytorch

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch

Determined Environments

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

PyTorch and some libraries

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch

Torch or Numpy? 用numpy还是Torch Torch 自称为神经网络界的 Numpy, 因为他能将 torch 产生的 tensor 放在 GPU 中加速运算 (前提是你有合适的 GPU), 就像 Numpy 会把 array 放在 CPU 中加速运算. 所以神经网络的话, 当然是