Skip to content

Latest commit

 

History

History
139 lines (72 loc) · 10.2 KB

notebooks.rst

File metadata and controls

139 lines (72 loc) · 10.2 KB
Raw

Notebooks List

Here we have a list of example notebooks using Torchbearer with a brief description of the contents and broken down by broad subject.

General

  • Quickstart Guide:

    This guide will give a quick intro to training PyTorch models with Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/quickstart.ipynb>   colab Run on Colab

  • Callbacks Guide:

    This guide will give an introduction to using callbacks with Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/callbacks.ipynb>   colab Run on Colab

  • Imaging Guide:

    This guide will give an introduction to using the imaging sub-package with Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/imaging.ipynb>   colab Run on Colab

  • Serialization:

    This guide gives an introduction to serializing and restarting training in Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/serialization.ipynb>   colab Run on Colab

  • History and Replay:

    This guide gives an introduction to the history returned by a trial and the ability to replay training.

    nbviewer Preview   Download Notebook </_static/notebooks/history.ipynb>   colab Run on Colab

  • Custom Data Loaders:

    This guide gives an introduction on how to run custom data loaders in Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/custom_loaders.ipynb>   colab Run on Colab

  • Data Parallel with Torchbearer:

    This guide gives a brief introduction on how to use PyTorch DataParallel with Torchbearer models.

    nbviewer Preview   Download Notebook </_static/notebooks/data_parallel.ipynb>   colab Run on Colab

  • LiveLossPlot with Torchbearer:

    This guide shows how we can get live loss visualisations in notebooks with LiveLossPlot.

    nbviewer Preview   Download Notebook </_static/notebooks/livelossplot.ipynb>   colab Run on Colab

  • PyCM with Torchbearer:

    This guide shows how we can generate confusion matrices with PyCM in torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/pycm.ipynb>   colab Run on Colab

  • Nvidia Apex with Torchbearer:

    This guide shows how we can do half and mixed precision training in torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/apex_torchbearer.ipynb>   colab Run on Colab

Deep Learning

  • Training a VAE:

    This guide covers training a variational auto-encoder (VAE) in Torchbearer, taking advantage of the persistent state.

    nbviewer Preview   Download Notebook </_static/notebooks/vae.ipynb>   colab Run on Colab

  • Training 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.

    nbviewer Preview   Download Notebook </_static/notebooks/gan.ipynb>   colab Run on Colab

  • Class 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

    nbviewer Preview   Download Notebook </_static/notebooks/cam.ipynb>   colab Run on Colab

  • Adversarial Example Generation:

    This guide will cover how to perform a simple adversarial attack in Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/adversarial.ipynb>   colab Run on Colab

  • Transfer Learning:

    This guide will cover how to perform transfer learning of a model with Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/transfer_learning.ipynb>   colab Run on Colab

  • Regularising Models:

    This guide will cover how to use Torchbearers built-in regularisers.

    nbviewer Preview   Download Notebook </_static/notebooks/regularisers.ipynb>   colab Run on Colab

Differentiable Programming

  • Optimising Functions:

    This guide will briefly show how we can do function optimisation using Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/basic_opt.ipynb>   colab Run on Colab

  • Linear SVM:

    This guide will train a linear support vector machine (SVM) using Torchbearer.

    nbviewer Preview   Download Notebook </_static/notebooks/svm_linear.ipynb>   colab Run on Colab

  • Breaking 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.

    nbviewer Preview   Download Notebook </_static/notebooks/amsgrad.ipynb>   colab Run on Colab