Create and train a PyTorch model for digit classification
Introduction
Prepare a PyTorch development environment
Create a PyTorch model for MNIST
About PyTorch model training
Perform training and save the model
Use the model for inference
Understand inference on Android
Create an Android application
Prepare Test Data
Run the Application
Optimizing neural network models in PyTorch
Create an optimized PyTorch model for MNIST
Run optimization
Update the Android application
Review
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

What you've learned

You should now know how to:

  • Prepare a PyTorch development environment.
  • Download and prepare the MNIST dataset.
  • Create a neural network architecture using PyTorch.
  • Train a neural network using PyTorch.
  • Create an Android app and loading the pre-trained model.
  • Prepare an input dataset.
  • Measure the inference time.
  • Optimize a neural network architecture using quantization and fusing.
  • Use an optimized model in the Android application.

Knowledge Check

Does the input layer of the model flatten the 28x28 pixel image into a 1D array of 784 elements?

Will the model make random predictions if it’s run before training?

Which loss function was used to train the PyTorch model on the MNIST dataset?


Back
Next