Adversarial domain adaptation methods.

This example illustrates the adversarial methods from on a simple image classification task.

# Author: Théo Gnassounou
#
# License: BSD 3-Clause
# sphinx_gallery_thumbnail_number = 4

from skorch import NeuralNetClassifier
from torch import nn

from skada.datasets import load_mnist_usps
from skada.deep import DANN
from skada.deep.modules import MNISTtoUSPSNet

Load the image datasets

dataset = load_mnist_usps(n_classes=2, n_samples=0.5, return_dataset=True)
X, y, sample_domain = dataset.pack_train(as_sources=["mnist"], as_targets=["usps"])
X_test, y_test, sample_domain_test = dataset.pack_test(as_targets=["usps"])

/home/circleci/project/skada/datasets/_mnist_usps.py:72: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  mnist_target = torch.tensor(mnist_dataset.targets)

Train a classic model

model = NeuralNetClassifier(
    MNISTtoUSPSNet(),
    criterion=nn.CrossEntropyLoss(),
    batch_size=128,
    max_epochs=5,
    train_split=False,
    lr=1e-2,
)
model.fit(X[sample_domain > 0], y[sample_domain > 0])
model.score(X_test, y=y_test)

  epoch    train_loss     dur
-------  ------------  ------
      1        1.5304  2.7989
      2        0.2732  2.7034
      3        0.0964  2.5977
      4        0.0555  3.0986
      5        0.0359  3.1007

0.9260450160771704

Train a DANN model

model = DANN(
    MNISTtoUSPSNet(),
    layer_name="fc1",
    batch_size=128,
    max_epochs=5,
    train_split=False,
    reg=0.01,
    num_features=128,
    lr=1e-2,
)
model.fit(X, y, sample_domain=sample_domain)
model.score(X_test, y_test, sample_domain=sample_domain_test)

/home/circleci/.local/lib/python3.10/site-packages/torch/nn/modules/module.py:1739: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
  return self._call_impl(*args, **kwargs)
  epoch    train_loss     dur
-------  ------------  ------
      1        2.4363  6.6828
      2        1.2963  7.3972
      3        1.1106  7.1004
      4        1.0687  8.1048
      5        1.0472  6.6900

0.8681672025723473