tensorpix/benchmarking-cv-models

Benchmark computer vision ML models in 3 minutes

32
/ 100
Emerging

This project helps machine learning teams evaluate the performance of different GPUs when training or inferencing computer vision models. You input the desired model architecture (like ResNet50 or UNet), specify GPU configurations, and get metrics like images per second and megapixels per second, which helps you choose the most cost-effective hardware for your deep learning workloads. It's designed for ML engineers or researchers making hardware purchasing decisions.

No commits in the last 6 months.

Use this if you need to benchmark the training or inference speed of popular computer vision models on various GPU setups to inform hardware procurement or optimization.

Not ideal if you need to benchmark a complete MLOps pipeline including data loading, preprocessing, or model saving, as this focuses only on the pure training/inference loop.

GPU benchmarking computer vision deep learning hardware ML model training performance optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

33

Forks

3

Language

Python

License

MIT

Last pushed

Jun 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tensorpix/benchmarking-cv-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.