ML model optimization product to accelerate inference.

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

Sparsity-aware deep learning inference runtime for CPUs

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

This is an official implementation for "Video Swin Transformers".

Revisiting Test Time Adaptation Under Online Evaluation

[CVPR'23 Highlight] AutoAD: Movie Description in Context.

[CVPR2023] All in One: Exploring Unified Video-Language Pre-training

Reverse engineered ChatGPT API

Ongoing research training transformer language models at scale, including: BERT & GPT-2

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

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

Refine high-quality datasets and visual AI models

[NeurIPS 2022] Egocentric Video-Language Pretraining

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

Torch modules that wrap blackbox combinatorial solvers according to the method presented in "Differentiating Blackbox Combinatorial Solvers"

Video datasets

cs20si learning note https://ghli.org/

Berkeley Deep Reinforcement Learning cs294 solution

Deep reinforcement learning agents implement by tensorflow https://ghli.org

Tensorflow Repo for "DeepGCNs: Can GCNs Go as Deep as CNNs?" ICCV2019 Oral https://www.deepgcns.org

SGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org

cs231n assignments sovled by https://ghli.org

The final project for the biomechatronics course, 201620.

List of all countries in different formats (ISO, tld, capital, language, population)

Efficient, reusable RNNs and LSTMs for torch