# CRAM CV EDUCATIONAL ROUND — Data

来源：https://www.kaggle.com/competitions/cram-cv-educational-round/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Dataset Description
## Task
Participants have to train a model for deep hallucination classification. This is a multi-way classification task in which an image must be classified into one of the 96 classes.

The training data is composed of 12,000 image files. The validation set is composed of 1,000 image files. The test is composed of 5,000 image files.

## File Descriptions
train.csv - the training metadata file containing the training image file names and the corresponding labels (one example per row)
val.csv - the validation metadata file containing the validation image file names and the corresponding labels (one example per row)
test.csv - the test metadata file containing only the test image file names (one sample per row without label)
sample_submission.csv - a sample submission file in the correct format
## Data Format
### Metadata Files
The metadata files are provided in the following format based on comma separated values:

Image,Class
12953.png,38
02978.png,76
10718.png,18
...
Each line represents an example where:

The first column shows the image file name of the example.
The second column is the label associated to the example.
Image Files
The image files are provided in .png format.