데이터셋 탐색

Long-range arena (LRA) is an effort toward systematic evaluation of efficient transformer models. The project aims at establishing benchmark tasks/datasets using which we can evaluate transformer-based models in a systematic way, by assessing their generalization power, computational efficiency, memory foot-print, etc. Long-Range Arena is specifically focused on evaluating model quality under long-context scenarios. The benchmark is a suite of tasks consisting of sequences ranging from 1K to 16K tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. Description from: Long Range Arena : A Benchmark for Efficient Transformers

MulRan is a dataset for Place Recognition and SLAM. The datasets were recorded in urban areas and contain sensor data of a car that is equipped with a 3D LiDAR (OS1-64) and a rotating radar (Navtech CIR204-H). For each sequence, the car is revisiting places several times.