Here we have a list of example notebooks using Torchbearer with a brief description of the contents and broken down by broad subject.
Quickstart Guide:
This guide will give a quick intro to training PyTorch models with Torchbearer.
Preview
Download Notebook </_static/notebooks/quickstart.ipynb>
Run on ColabCallbacks Guide:
This guide will give an introduction to using callbacks with Torchbearer.
Preview
Download Notebook </_static/notebooks/callbacks.ipynb>
Run on ColabImaging Guide:
This guide will give an introduction to using the imaging sub-package with Torchbearer.
Preview
Download Notebook </_static/notebooks/imaging.ipynb>
Run on ColabSerialization:
This guide gives an introduction to serializing and restarting training in Torchbearer.
Preview
Download Notebook </_static/notebooks/serialization.ipynb>
Run on ColabHistory and Replay:
This guide gives an introduction to the history returned by a trial and the ability to replay training.
Preview
Download Notebook </_static/notebooks/history.ipynb>
Run on ColabCustom Data Loaders:
This guide gives an introduction on how to run custom data loaders in Torchbearer.
Preview
Download Notebook </_static/notebooks/custom_loaders.ipynb>
Run on ColabData Parallel with Torchbearer:
This guide gives a brief introduction on how to use PyTorch DataParallel with Torchbearer models.
Preview
Download Notebook </_static/notebooks/data_parallel.ipynb>
Run on ColabLiveLossPlot with Torchbearer:
This guide shows how we can get live loss visualisations in notebooks with LiveLossPlot.
Preview
Download Notebook </_static/notebooks/livelossplot.ipynb>
Run on ColabPyCM with Torchbearer:
This guide shows how we can generate confusion matrices with PyCM in torchbearer.
Preview
Download Notebook </_static/notebooks/pycm.ipynb>
Run on ColabNvidia Apex with Torchbearer:
This guide shows how we can do half and mixed precision training in torchbearer.
Preview
Download Notebook </_static/notebooks/apex_torchbearer.ipynb>
Run on Colab
Training a VAE:
This guide covers training a variational auto-encoder (VAE) in Torchbearer, taking advantage of the persistent state.
Preview
Download Notebook </_static/notebooks/vae.ipynb>
Run on ColabTraining a GAN:
This guide will cover how to train a Generative Adversarial Network (GAN) in Torchbearer using custom closures to allow for the more complicated training loop.
Preview
Download Notebook </_static/notebooks/gan.ipynb>
Run on ColabClass Appearance Model:
In this example we will demonstrate the ClassAppearanceModel callback included in torchbearer. This implements one of the most simple (and therefore not always the most successful) deep visualisation techniques, discussed in the paper Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Preview
Download Notebook </_static/notebooks/cam.ipynb>
Run on ColabAdversarial Example Generation:
This guide will cover how to perform a simple adversarial attack in Torchbearer.
Preview
Download Notebook </_static/notebooks/adversarial.ipynb>
Run on ColabTransfer Learning:
This guide will cover how to perform transfer learning of a model with Torchbearer.
Preview
Download Notebook </_static/notebooks/transfer_learning.ipynb>
Run on ColabRegularising Models:
This guide will cover how to use Torchbearers built-in regularisers.
Preview
Download Notebook </_static/notebooks/regularisers.ipynb>
Run on Colab
Optimising Functions:
This guide will briefly show how we can do function optimisation using Torchbearer.
Preview
Download Notebook </_static/notebooks/basic_opt.ipynb>
Run on ColabLinear SVM:
This guide will train a linear support vector machine (SVM) using Torchbearer.
Preview
Download Notebook </_static/notebooks/svm_linear.ipynb>
Run on ColabBreaking ADAM:
This guide uses Torchbearer to implement On the Convergence of Adam and Beyond, one of the top papers at ICLR 2018, which demonstrated a case where ADAM does not converge.
Preview
Download Notebook </_static/notebooks/amsgrad.ipynb>
Run on Colab