A simple synthetic dataset and baseline model for visual counting.
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.
NOTE: This is not a dataset to beat, but a simple place to start for validating ideas in counting models.
python -m counting_mnist.create_dataset
python -m counting_mnist.main
| Model | Accuracy |
|---|---|
| Always Predict Zero Even Digits | 33% |
| Uniform Count Predictions | 12% |
| Baseline Model | 85% |