Welcome to Shadow’s Documentation!

Shadow is a PyTorch based library for semi-supervised machine learning. The shadow python 3 package includes implementations of Virtual Adversarial Training, Mean Teacher, and Exponential Averaging Adversarial Training. Semi-supervised learning enables training a model (gold dashed line) from both labeled (red and blue) and unlabeled (grey) data, and is typically used in contexts in which labels are expensive to obtain but unlabeled examples are plentiful.


Github development page:



Shadow can be installed directly from pypi as:

pip install shadow-ssml

Hello World

Incorporating consistency regularizers into an existing supervised workflow for semi-supervised learning is straightforward. First, Shadow provides techniques that wrap an existing PyTorch model:

model = ...  # PyTorch torch.nn.Module
eaat = shadow.eaat.Eaat(model)  # Wrapped model

The wrapped model is used during training and inference. The model wrapper provides a get_technique_cost method for computed the consistency cost based on unlabeled data. This loss can be added to an existing loss computation to enable semi-supervised learning:

for x, y in trainloader:
    # zero the parameter gradients

    # forward pass
    outputs = eaat(x)

    # get semi-supervised loss, using supervised criterion and unsupervised criterion
    # provided by the model wrapper
    loss = criterion(x, y) + eaat.get_technique_cost(x)

For a full working example, see the MNIST Example.

Citing Shadow

To cite shadow, use the following reference:

  • Linville, Lisa, et al. “Semi-supervised learning for seismic monitoring applications”. In preparation. (2020).

Indices and tables

Sandia National Laboratories is a multimission laboratory managed and operated by National Technology and Engineering Solutions of Sandia LLC, a wholly owned subsidiary of Honeywell International Inc. for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.