# UCSD Deep Learning Class Competition — Data

来源：https://www.kaggle.com/competitions/cse151b-spring2022/data

采集时间：2026-10-19T08:57:38Z

This page describes the details of the dataset. We provide the training set and the input of the test set. You are requested to submit the output (predictions) for the test set. The test set is further split into 80% for the public leaderboard and 20% for the private leaderboard.

We also provide a sample submission file with zero predictions. You are expected to replace the zeros with the predictions generated by your deep learning model.



## Files

*   **train** - the training set folder
*   **test** - the test set folder
*  **Load_Argo2_Publlic.ipynb** - a jupyter notebook to load the data 
*   **sample_submission.csv** - a sample submission file in the correct format

## Format

*   `austin_input` - input trajectories in Austin. A numpy array with the shape ( N, 50, 2). N is the number of scenes. 50 is the input 50 time steps. 2 is the x and y dimension.
*   `austin_output` - output trajectories in Austin. A numpy array with the shape ( N, 60, 2). N is the number of scenes. 60 is the output 60 time steps. 2 is the x and y dimension.
*   same for all other cities