huggingface/evaluate
A Python library from Hugging Face for standardized evaluation of machine learning models using plug-in metrics and measurement tools.
Not currently ranked — collecting fresh signals.
star history
🤗 Evaluate is a library that makes evaluating and comparing models and reporting their performance easier and more standardized. It provides implementations of dozens of popular metrics spanning NLP to Computer Vision tasks, allowing users to load metrics like accuracy = load("accuracy") and evaluate ML models across any framework including Numpy, Pandas, PyTorch, TensorFlow, and JAX. The library also offers comparison and measurement tools to evaluate model performance.
Frequently asked
- What is huggingface/evaluate?
- A Python library from Hugging Face for standardized evaluation of machine learning models using plug-in metrics and measurement tools.
- Is evaluate open source?
- Yes — huggingface/evaluate is open source, released under the Apache-2.0 license.
- What language is evaluate written in?
- huggingface/evaluate is primarily written in Python.
- How popular is evaluate?
- huggingface/evaluate has 2.5k stars on GitHub.
- Where can I find evaluate?
- huggingface/evaluate is on GitHub at https://github.com/huggingface/evaluate.