lfwa / carbontracker
Track and predict the energy consumption and carbon footprint of training deep learning models.
☆363Updated this week
Related projects: ⓘ
- ☆266Updated 7 months ago
- ML has an impact on the climate. But not all models are born equal. Compute your model's emissions with our calculator and add the result…☆198Updated 2 months ago
- Track emissions from Compute and recommend ways to reduce their impact on the environment.☆1,087Updated this week
- Provides a function to measure the energy usage of another function.☆154Updated 3 years ago
- OpenXAI : Towards a Transparent Evaluation of Model Explanations☆227Updated last month
- 🌱 The Green AI Standard aims to develop a standard and raise awareness for best environmental practices in AI research and development☆80Updated 3 years ago
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆526Updated last month
- 👋 Xplique is a Neural Networks Explainability Toolbox☆620Updated this week
- A Python library to capture the energy consumption of code snippets☆69Updated last year
- A library to inspect and extract intermediate layers of PyTorch models.☆469Updated 2 years ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆191Updated 2 months ago
- Enabling easy statistical significance testing for deep neural networks.☆324Updated 2 months ago
- scikit-activeml: Python library for active learning on top of scikit-learn☆147Updated this week
- The WeightWatcher tool for predicting the accuracy of Deep Neural Networks☆1,440Updated last week
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆546Updated 7 months ago
- Drift Detection for your PyTorch Models☆310Updated 2 years ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆26Updated 5 months ago
- Metrics to evaluate quality and efficacy of synthetic datasets.☆201Updated this week
- Benchmarking synthetic data generation methods.☆254Updated this week
- Croissant is a high-level format for machine learning datasets that brings together four rich layers.☆406Updated last week
- A repository for explaining feature attributions and feature interactions in deep neural networks.☆185Updated 2 years ago
- Datasets derived from US census data☆232Updated 4 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆110Updated 3 months ago
- Frouros: an open-source Python library for drift detection in machine learning systems.☆184Updated last month
- Papers and code of Explainable AI esp. w.r.t. Image classificiation☆191Updated 2 years ago
- A basic framework for your PyTorch projects☆73Updated 4 years ago
- Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥…☆436Updated this week
- ☆132Updated 10 months ago
- Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using co…☆317Updated last year
- Train Gradient Boosting models that are both high-performance *and* Fair!☆102Updated 3 months ago