Efficient-Computing
by huawei-noah
Efficient computing methods developed by Huawei Noah's Ark Lab
AI summary
Neural network optimization tools
A collection of research methods and techniques developed by Huawei to improve the efficiency of neural networks in computer vision and other applications.
- stars
- 1.2K
- forks
- 212
- watching
- 24
Similar projects
Found by comparing what the projects do, not just their names.
Network tuner
Automates the search for optimal neural network configurations in deep learning applications
Image processor
This project develops a pre-trained transformer model for image processing tasks such as denoising, super-resolution, and deraining.
Model optimizer
Tools and techniques for optimizing large language models on various frameworks and hardware platforms.
AutoML pipeline
An AutoML toolchain with a pipeline of Hyperparameter Optimization, Data Augmentation, Network Architecture Search, Model Compression, and Fully Train capabilities
Hardware-aware NAS
Direct neural architecture search on target task and hardware for efficient model deployment
Hyperopt tuner
Automates hyperparameter optimization and neural network architecture search using Hyperopt on a CNN model for the CIFAR-100 dataset
CNN optimizer
A tool for exploring and optimizing the architecture of Convolutional Neural Networks using a Genetic Algorithm
EfficientNet model
A PyTorch implementation of EfficientNet for computer vision tasks
GAN trainer
Improves GAN training efficiency by incorporating data augmentation
Model optimizer
Enables the creation of smaller neural network models through efficient pruning and quantization techniques
AutoML Tool
An autoML tool that searches and optimizes neural network architectures using tensorflow and keras.
Neural network library
A lightweight C library for constructing and training small to medium neural networks with customizable architecture
GNNs
An implementation of graph neural networks for solving combinatorial optimization problems
Hyperparameter Tuner
Provides tools and techniques for tuning hyperparameters in machine learning models to improve performance.
Pruning tool
This project provides a PyTorch implementation of pruning techniques to reduce the computational resources required for neural network inference.
