AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Official implementation of Half-Quadratic Quantization (HQQ)

Free, open-source network communication library for image-guided therapy

Framework to transform natural language into formal language (Temporal Logics).

Activation-aware Singular Value Decomposition for Compressing Large Language Models

[인프런] 운영체제 공룡책 강의, 정리

Neural Network Quantization With Fractional Bit-widths

대신증권의 크레온API사용한 매수매도 자동화 프로그램

A simple baseline for one-shot multi-object tracking

리디 페이퍼 프로용 타사 앱 실행 및 루트 도구

On-device Neural Engine

Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)

A mobilenet SSD based face detector, powered by tensorflow object detection api, trained by WIDERFACE dataset.

this repository is for the NVIDIA AI Developers Day 2019 at South Korea

SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction). "M. Zhang, Y. Chen, Link Prediction Based on Graph Neural Networks, NIPS 2018 spotlight".

tensorflow-as-gcn

Representation learning on large graphs using stochastic graph convolutions.

Python library to easily log experiments and parallelize hyperparameter search for neural networks

The sample codes for our ICLR18 paper "FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling""

Implementation of the paper "Community Detection with Graph Neural Networks", by J. Bruna and L. Li

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Sample Code for Gated Graph Neural Networks

Deep network that performs spectral clustering

Implementation of Graph Auto-Encoders in TensorFlow

Topics course Mathematics of Deep Learning, NYU, Spring 18