MindSpore Quick Start: An End-to-End MNIST Classifier
The MNIST dataset contains 60,000 training and 10,000 test grayscale images of handwritten digits, each 28×28 pixels. A complete MindSpore workflow loads this data, defines a feed-forward neural network, optimizes the parameters, and persists the trained weights.
Data Loading
Place the raw files under MNIST_Data/ with train/ and test/ subdirect ...
Posted on Sat, 05 Sep 2026 16:53:12 +0000 by who_cares
Building and Training Neural Networks from Scratch: Data Handling, Augmentation, and Model Deployment
Creating Custom Datasets
When working with standard datasets like MNIST, data is prepackaged and ready for use. However, for domain-specific applications, creating custom datasets becomes essential.
The process involves mapping image paths to corresponding labels through a dedicated function that returns features and their associated labels.
To ...
Posted on Mon, 06 Jul 2026 16:40:47 +0000 by Butthead