← Back to courses
Artificial Intelligence and Machine Learning
Deep Learning with PyTorch
Tensors, training loops and neural networks you build yourself
A classroom course in building and training neural networks. The first seven modules are the seven steps of PyTorch's own "Learn the Basics" series: tensors, datasets and data loaders, transforms, building a model, automatic differentiation, the optimization loop, and saving and loading. The rest apply them to images and text. This course prepares for no exam.
11Modules
IntermediateLevel
3 monthsDuration
COURSE THUMBNAIL
What you will be able to do
Work with tensors and load data efficiently
Define a neural network and write its training loop
Explain what automatic differentiation does during training
Train an image classifier and improve it with transfer learning
Save a trained model and use it for predictions
Course outline
01
Tensors
02
Datasets and DataLoaders
03
Transforms
04
Building a neural network
05
Automatic differentiation
06
The optimization loop
07
Saving, loading and using a model
08
Convolutional networks for images
09
Transfer learning with a pretrained model
10
Sequence models for text
11
Project: train, evaluate and present a model
Tools you will use
PyTorchtorchvisionPythonNumPyJupyter
What you need
Comfortable programming in Python
Machine learning basics (Machine Learning with Python and scikit-learn or equivalent)
