🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Self-contained, minimalistic implementation of diffusion models with Pytorch.

Neural Network implementation in Numpy and Keras. Batch Normalization, Dropout, L2 Regularization and Optimizers

Object trackers using Kalman filter and particle filter with MATLAB

Pytorch文本分类(imdb数据集)，包含DataLoader数据加载，最优模型保存

手搓一个简单的神经网络识别猫咪，纯numpy实现。