# DT8028_2024 — Data

来源：https://www.kaggle.com/competitions/DT-8028-2024-2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Class Separated KITTI or ClaSeK is derived from semanticKITTI dataset. Instead of semantic segmentaiton is dataset is processed for classificaiton. There are originally 16 classes, two more classes are added to prevent discovering the results with trial and error method.

### **Labels**
0: "car"
1: "bicycle"
2: "motorcycle"
3: "truck"
4: "other_vehicle"
5: "person"
6: "motorcyclist"
7: "road"
8: "parking"
9: "sidewalk"
10: "other_ground"
11: "building"
12: "fence"
13: "vegetation"
14: "trunk"
15: "terrain"
16: "pole"
17: "traffic_sign"

### **Files**
data - folder hosts the subfolder for training and testing point clouds
train.csv - the training set
test.csv - the test set
sample_submission.csv - a sample submission file in the correct format

### **Columns**
FNAME - is the file name from concerning split.
LABEL - is the label of the point cloud