DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch

The author's officially unofficial PyTorch BigGAN implementation.

stock，股票系统。使用python进行开发。

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

PyTorch ,ONNX and TensorRT implementation of YOLOv4

A student implementation of Alpha Go Zero

Implementation of "DeepShift: Towards Multiplication-Less Neural Networks" https://arxiv.org/abs/1905.13298

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Semantic Image Synthesis with SPADE

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.

A PyTorch implementation of EfficientNet

A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

从2019年4月起完成的各种人工智能相关工程

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Machine learning, in numpy

Tensors and Dynamic neural networks in Python with strong GPU acceleration

CAM图的resnet50版本

A Hyperparameter Tuning Library for Keras

Stronger SSD & YOLO v3

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.