A simple synthetic dataset and baseline model for visual counting. The task is to count the number of even digits given a 100x100 image, each with up to 5 randomly chosen MNIST digits.
We use rejection sampling to ensure digits are separated by at least 28 pixels. Reproduced with details from Learning to count with deep object features.
View it on Github: https://github.com/fomorians/counting-mnist
git clone [email protected]:fomorians/counting-mnist.git
python -m counting_mnist.create_dataset
python -m counting_mnist.main
|Always Predict Zero Even Digits||33%|
|Uniform Count Predictions||12%|
NOTE: This is not a competitive dataset, it’s intended to be simple place to start for validating ideas in counting models.