Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 648 Bytes

README.md

File metadata and controls

2 lines (2 loc) · 648 Bytes

Digit-Recognition-python

The MNIST database is a set of 70000 samples of handwritten digits where each sample consists of a grayscale image of size 28×28. There are a total of 70,000 samples. We will use sklearn.datasets package to download the MNIST database from mldata.org. This package makes it convenient to work with toy datasbases.The size of of MNIST database is about 55.4 MB. Once the database is downloaded, it will be cached locally in your hard drive. On my Linux system, by default it is cached in ~/scikit_learn_data/mldata/mnist-original.mat . Alternatively, you can also set the directory where the database will be downloaded.