Checklist Cyprus AI Camp 2026 IOAI Selection Camp · Task 3
Fashion Classifier
Classify Fashion-MNIST images into 10 clothing categories with a PyTorch model.
The task
The dataset is Fashion-MNIST: 28×28 grayscale images of fashion items in 10 balanced classes (T-shirt/top, trouser, pullover, dress, coat, sandal, shirt, sneaker, bag, ankle boot).
The statement recommends PyTorch ('as specified in IOAI rules') and gives hints on normalisation, a simple CNN, augmentation and regularisation.
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
train_images.npy(60,000×28×28),train_labels.npy,public_test_images.npyandprivate_test_images.npy(5,000 each),sample_submission.csv.- You submit
- CSV with Id (0–9999) and Category (0–9).
- Scoring
- Accuracy; points = min(100, 3.2 × e^(13.9 × (accuracy − 0.75)) − 3.2).
- Rules
- Pre-trained models and additional data are not allowed unless the task says otherwise.
- No outside help; LLM chats, ChatGPT, Copilot and similar tools are prohibited (except Colab inline autocompletion).
- Only the Kaggle website and Google Colab may be used (no local IDEs); online library documentation is allowed.
- One Kaggle account per participant; leaderboard name '[City] Name Surname'.
- Format
- Cyprus AI Camp 2026 (IOAI 2026 selection, in person, 31 Jan–8 Feb 2026): ML Images 1, released 3 Feb 2026, 09:00–12:00 EET, on Kaggle (two tasks per 3-hour session).