# Important Rule
You need to use your URN as the Team Name in the Kaggle page. Otherwise, your score won't be recorded.

# Code Submission
You need to submit your code to Surreylearn before the code submission due date (see SurreyLearn for further detail)

# Participation
Please click the join competition button on the page to join it. Otherwise, you cannot submit your result.

# Task 
### Overview
This is a dataset about **Visual Object Classification**. The goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes. There are twenty-three object classes in the datasets:

### Dataset Size
- Training set: 5011 images
- Testing set: 4952 images

### Training and Testing Data
We will provide the images and labels for the training set and images for the testing set.

# Evaluation
We will evaluate your prediction result on the testing set. So you will need to submit the result on this competition page. **The minimum requirement of this challenge is 1.0 Mean ColumnWise Log Loss (lower result indicate better performance).**
 
# Submission Format
Your submission should be a csv file, with 24 columns in it, the first is the id of the test image and the second to 24th are the predicted probability of each visual object class (e.g., person 0.49, cat 0.97, dog 0.01). We will provide an example of the submission file in the Data Section.