The TuSimple dataset contains 6,408 images of US highways with a resolution of 1280 × 720. The dataset consists of 3,626 images for training, 358 images for validation, and 2,782 images for testing (called the TuSimple test set), all of which were taken under different weather conditions..This dataset was released by Qualcomm in 2020, and the related paper results are "End-to-End Lane Marker Detection via Row-wise Classification".