CodeXGLUE is a benchmark dataset and open challenge for code intelligence. It includes a collection of code intelligence tasks and a platform for model evaluation and comparison. CodeXGLUE stands for General Language Understanding Evaluation benchmark for CODE. It includes 14 datasets for 10 diversified code intelligence tasks covering the following scenarios:
34 PAPERS • 15 BENCHMARKS
The dataset is constructed from images of defective production items that were provided and annotated by Kolektor Group d.o.o.. The images were captured in a controlled industrial environment in a real-world case.
5 PAPERS • 3 BENCHMARKS
This is a synthetic dataset for defect detection on textured surfaces. It was originally created for a competition at the 2007 symposium of the DAGM (Deutsche Arbeitsgemeinschaft für Mustererkennung e.V., the German chapter of the International Association for Pattern Recognition). The competition was hosted together with the GNSS (German Chapter of the European Neural Network Society).
3 PAPERS • 2 BENCHMARKS