Striveworks, an MLOps platform provider, has launched an open-source tool for model performance evaluation named Valor.
Valor aids in determining the best model for a given dataset, tracks variations in the performance of a single model over different datasets, and observes how subtle differences in data segments influence a model's performance.
The tool supports computer vision models designed for image segmentation, object detection, and image classification alongside various models for classification tasks. The company plans to expand its support to include additional use cases and model varieties in upcoming iterations.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.