CINIC-10 Image Classification Challenge
Classify the images in the dataset belonging to their respective categories.
Welcome to CINIC-10 Image Classification Challenge
CINIC-10 is a drop-in replacement for CIFAR-10. It is compiled as a bench-marking dataset because CIFAR-10 can be too small/too easy and ImageNet is often too large/difficult. CINIC-10 fills this bench-marking gap. CINIC-10 has a total of 270,000 images equally split into three subsets: train, validate, and test. In each subset (90,000 images) there are ten classes (identical to CIFAR-10 classes). There are 9,000 images per class per subset.
CINIC-10 is not ImageNet or CIFAR-10, https://arxiv.org/abs/1810.03505
The dateset includes 10 training directories with images corresponding to classes and 1 test directory.
The output has to be generated for the "test" directory having 90,000 images.
The final submission must include:
output.csv (single file having results for "test" directory which contains 90,000 images )
For grading, "output.csv" file must be uploaded in the submission section of this challenge.
The first row should correspond to the column names "filename" and "label".
- You must submit your CSV file by uploading the CSV in the "My Submissions" section of this challenge.
- Your submission will be auto graded and you will be able to see your results instantly.
- If there is any error in the submission, your final score will be marked as 0.
- Accuracy Score
- The submission should be in a proper format as described by "Submission Guidelines".
- 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.
- Top three participants will get a place in Hall of Fame page.