## Competition details

The details of this competition will be shared in a separate resource.

The BloodMNIST dataset is part of the wider MedMNIST dataset.

MedMNIST is a large-scale MNIST-like collection of standardized biomedical images, including twelve 2D datasets and six 3D datasets. All the images are pre-processed to the size of 28x28 pixels and working with the data requires no prior domain knowledge about medicine, genetics, biology, etc.

## BloodMNIST details

The BloodMNIST is based on a dataset of individual normal cells, captured from individuals without infection, hematologic or oncologic disease and free of any pharmacologic treatment at the moment of blood collection. It contains a total of 17,092 images and is organized into 8 classes (8 different classes of blood cell).


## Spoiler

If you'd like *a* solution to the proposed classification task we've included one that was authored by our colleagues Justin and Ayush here: [Integrating Keras with Weights and Biases](https://wandb.ai/ayush-thakur/medmnist-bloodmnist/reports/Integrating-Keras-with-Weights-Biases--VmlldzoxNDg1MDQy?utm_source=webinar&utm_medium=online&utm_campaign=windsor).