# UCSD Deep Learning Class Competition — Data

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

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<p>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.  </p>
<p> 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. </p>

<h2>File descriptions</h2>
<ul>
<li><strong>new_train</strong> - the training set including the output labels</li>
<li><strong>new_val_in</strong> - the test set with the inputs only</li>
<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>
</ul>
<h2>Data fields</h2>
<p>Every pickle is a scene with trajectory tracking sequences for a maxium of 60 vehicles recorded at 10HZ (10 records per second). The target vehicle is called agent with a corresponding agent_id. Track_id is a sequence of IDs that track the ID of all vehicles including the agent itself.  The pickle file contains a dictionary with the following keys/values 
<ul>
<li><strong>p_in</strong>-the (x,y) position input in the first two seconds (19 time steps) </li>
<li><strong>v_in</strong>-the (x,y) velocity input in the first two seconds (19 time steps) </li>
<li><strong>p_out</strong>- the (x,y) position output in the next three seconds (30 time steps)</li>
<li><strong>v_out </strong>- the (x,y) velocity output in the next three seconds (30 time steps)</li>
<li><strong>track_id</strong>- the track_id for each vehicle in the output sequence (30 time steps) </li>
<li><strong>scene_idx</strong>- the id of this scene</li>
<li><strong>agent_id</strong>- track id for the agent in this scene</li>
<li><strong>car_mask</strong>- boolean index for the real car, we need to align the car numbers</li>
<li><strong>lane</strong>- (x,y) for centerline nodes in this scene</li>
<li><strong>lane_norm</strong>- the direction of each lane node</li>
</ul>

<h2>Submission Format</h2>
You will submit a csv file with 3,201 rows and 61 columns. The first row is the header indicating ID, v1, v2...
The first column corresponds to scene_idx. The rest of the 60 columns are p_out (x,y) over 30 time steps.