Loading and Exploring MNIST Dataset
Image Classification Task
MNIST is a classic computer-vision dataset used for handwritten digits recognition. The dataset consists of:
black and white images of handwritten digits
10 classes
28x28 pixels
7 000 images per classes
60 000 images in the training set
10 000 images in the test set
Download and Load MNIST Dataset
Training Tensor Shape
Testing Tensor Shape
Ploting Helper Function
Explore MNIST Dataset
Next Lesson
ACGAN Architecture
Discriminator
Generator
Label Conditioning
Last updated