Library/nasbenchForked

google-research/nasbench

nasbench

NASBench: A Neural Architecture Search Dataset and Benchmark

View on GitHub↗Upstream google-research/nasbench↗

Builder

google-research

google-research • individual

Stars

717

Using upstream star count

Forks

129

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Dec 21, 2018

Project creation date

README Summary

NASBench is a tabular dataset and benchmark for Neural Architecture Search (NAS) that contains over 400,000 unique neural network architectures trained on CIFAR-10. It provides precomputed results for validation accuracy, test accuracy, and training time to enable reproducible NAS research. The dataset eliminates the need to train architectures from scratch, making NAS algorithm evaluation much faster and more accessible.

AI Dev Skills

Unmapped

Neural Architecture SearchAutoMLNeural Network DesignDeep Learning BenchmarkingHyperparameter OptimizationModel Architecture OptimizationConvolutional Neural Networks

Taxonomy

AI Trends

AutoML Neural Architecture Search Automated Machine Learning

Deployment Context

Self-hosted

Modalities

Image

Skill Areas

Neural Architecture Search AutoML Neural Network Design Deep Learning Benchmarking Hyperparameter Optimization Model Architecture Optimization Convolutional Neural Networks

Use Cases

Neural Architecture Search Algorithm Development AutoML Method Benchmarking Architecture Performance Prediction NAS Algorithm Comparison Automated Neural Network Design

Recent Activity

Updated 2 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: high
Maturity: research

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created: Dec 21, 2018
Forked: Mar 23, 2026
Your last push: 2 years ago
Upstream last push: 2 years ago
Tracked since: May 1, 2023

Similar Repos

pgvector cosine similarity · $0

Loading…