Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Core deep-learning frameworks and libraries for pretraining and distributed training.
Signals: deep-learning, neural-network, pytorch, tensorflow, jax, distributed-training, training, deepspeed
2,672 results
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
Fast, flexible and easy to use probabilistic modelling in Python.
StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Notes about courses Dive into Deep Learning by Mu Li
OpenMMLab Pre-training Toolbox and Benchmark
Compute FID scores with PyTorch.
A highly efficient implementation of Gaussian Processes in PyTorch
Differentiable architecture search for convolutional and recurrent networks
A simplified implemention of Faster R-CNN that replicate performance from origin paper
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
Model summary in PyTorch similar to `model.summary()` in Keras
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
Pytorch 中文文档
PyTorch深度学习快速入门教程（绝对通俗易懂！）
LPIPS metric. pip install lpips
NeuralProphet: A simple forecasting package
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
LLM training code for Databricks foundation models
Noise supression using deep filtering
Lightning fast C++/CUDA neural network framework
A unified, comprehensive and efficient recommendation library
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
24,540 repositories in the index in total.
