Challenge has Ended

Caltech Image Classification Challenge

The aim of this challenge is to develop an image classifier for given categories.


115 Participants

Welcome to Caltech Image Classification AI Challenge!

The aim of this challenge is to develop an image classifier for given categories. RGB images of objects belonging to 256 categories are provided. It has about 40 to 800 images per category. The size of each image is roughly 300 x 200 pixels.

The unique categories can be determined using the training labels file "256_train.csv". The images can be of variable size, so the participants will have to adjust the sizes according to their models.


Griffin, G. Holub, AD. Perona, P. The Caltech 256

The dataset includes one training directory "256_train_imgs", training labels "256_train.csv" and test directory "256_test_imgs".

The output has to be generated for the "test" directory having 9,241 images having 256 output categories.

The final submission must include:

output.csv (single file having results for "test" directory which contains 9,241 images )

For grading, "output.csv" file must be uploaded in the "My Submission" section of this challenge.

The first row should correspond to the column names "Filename" and "Labels".

How to convert python dictionary to CSV?

# importing pandas as pd 
import pandas as pd 
# list of name, degree, score
nme = ["aparna", "pankaj", "sudhir", "Geeku"]
deg = ["MBA", "BCA", "M.Tech", "MBA"]
# dictionary of lists 
dict = {'name': nme, 'degree': deg} 
df = pd.DataFrame(dict)
# saving the dataframe
df.to_csv('file1.csv', index=False)

How to make a submission?

  1. Click on "My Submission"
  2. On the next page, click on "+ New Submission"
  3. Upload your CSV in the next page and click on "Submit for Review"

Please note:

  1. You must submit your CSV file by uploading the CSV in the "My Submissions" section of this challenge.
  2. Your submission will be auto graded and you will be able to see your results instantly.
  3. If there is any error in the submission, your final score will be marked as 0.


  1. Accuracy Score


  1. The submission should be in a proper format as described by "Submission Guidelines".
  2. Late submission will not be accepted beyond provided deadline (Indian Standard Time).

NOTE: We may request for the code files if there is any discrepancy in your score. Your score will be marked invalid if the request for code is not fulfilled by you.


  1. Top three participants will get a place in Hall of Fame page.

How do I apply for this Challenge?
How do I download the dataset?
Can I make multiple submissions?
Where will the results be declared?
Can we apply as a team?
I've other queries, where can I get support?
Challenge Announced
28-Aug-2020, 12:17 pm IST
01-Sept-2020, 6:00 pm IST
Challenge Started
Challenge Ended
23-Jan-2023, 6:00 pm IST