Deep learning sample data
You can use the IBM Watson Machine Learning following sample data sets to create deep learning models. These particular data sets can be used with sample neural network models, which are available when you create a neural network model from sample.
- The MNIST data - hand-written digits in PKL format consists of 60,000 training and 10,000 test examples of grayscale 28x28 images.
- The CIFAR-10 dataset in PKL format consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images