Category Archives: PyTorch

MNIST Image Classification Using PyTorch 1.10 on Windows 11

One of my standard neural network examples is image classification on the MNIST dataset. The full MNIST (modified National Institute of Standards and Technology) dataset has 60,000 images for training and 10,000 images for testing. Each image is a 28 … Continue reading

Posted in PAW, PyTorch | Leave a comment

Regression (Employee Income) Using PyTorch 1.10 on Windows 11

One of my standard neural network examples is to predict employee income from sex, age, city, and job-type. Predicting a single numeric value is usually called a regression problem. (Note: “logistic regression” predicts a single numeric probability value between 0.0 … Continue reading

Posted in PAW, PyTorch | 1 Comment

Autoencoder Anomaly Detection Using PyTorch 1.10 on Windows 11

Every few months I revisit my standard neural network examples to make sure that changes in the underlying code libraries (PyTorch, Keras/TensorFlow) haven’t introduced a breaking change(s). One of my standard examples is autoencoder anomaly detection. The idea is to … Continue reading

Posted in PAW, PyTorch | Leave a comment

Preparing a Machine for the 2022 Predictive Analytics World All-Day Workshop

I will be presenting an all-day, hands-on machine learning workshop at the 2022 Predictive Analytics World (PAW) and Machine Learning Week (MLW) events, on Monday, June 20, in Las Vegas. See https://www.predictiveanalyticsworld.com/machinelearningweek/. The PAW / MLW events have lots of … Continue reading

Posted in Keras, Machine Learning, PAW, PyTorch | Leave a comment

Installing PyTorch 1.10.0 on Windows 10/11

PyTorch is a neural network code library. Prerequisites: A machine with a relatively modern CPU (no older than 8 years old) running Windows 10 or 11, with Python 3.7.6 installed via the Anaconda 2020.02 distribution. See https://jamesmccaffrey.wordpress.com/2022/05/10/installing-anaconda3-2020-02-with-python-3-7-6-on-windows-10-11/. You must be … Continue reading

Posted in Keras, PAW, PyTorch | 2 Comments

Installing Anaconda3 2020.02 with Python 3.7.6 on Windows 10/11

Anaconda is a collection of software packages that contains a base Python engine plus over 500 compatible Python packages. You need to install Anaconda Python before you can install the PyTorch or Keras/TensorFlow neural network code libraries. See the links … Continue reading

Posted in Keras, Machine Learning, PAW, PyTorch | 1 Comment

The Boston Area House Price Problem Using PyTorch 1.10 on Windows 10/11

One of the standard datasets for machine learning regression problems is the Boston Area House dataset. The data has 506 items. Each item represents a town or village near Boston. The goal is to predict the median house price in … Continue reading

Posted in PyTorch | 1 Comment

Binary Classification Using PyTorch 1.10 on Windows 11

I’m in the process of preparing PyTorch machine learning training classes for employees at my company. One of my standard examples is binary classification. I use a set of synthetic Employee data that looks like: 1 0.24 1 0 0 … Continue reading

Posted in PAW, PyTorch | Leave a comment

Predicting Employee Job Type Using PyTorch 1.10 on Windows 11

Because the field of machine learning changes so quickly, it’s important to stay up to date with the latest versions of libraries such as Keras and PyTorch. One of my standard examples for PyTorch neural network classification is to predict … Continue reading

Posted in PAW, PyTorch | Leave a comment

CIFAR-10 Image Classification Using PyTorch in Visual Studio Magazine

I wrote an article titled “CIFAR-10 Image Classification Using PyTorch” in the April 2022 edition of Microsoft Visual Studio Magazine. See https://visualstudiomagazine.com/articles/2022/04/11/pytorch-image-classification.aspx. The article explains how to create a PyTorch image classification system for the CIFAR-10 dataset. CIFAR-10 images are … Continue reading

Posted in PyTorch | Leave a comment