Divergence domain adaptation methods.

This example illustrates the DeepCoral method from [1] 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 DeepCoral
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(
    as_sources=["mnist"], as_targets=["usps"], mask_target_labels=True
)
X_test, y_test, sample_domain_test = dataset.pack(
    as_sources=[], as_targets=["usps"], mask_target_labels=False
)
  0%|          | 0.00/9.91M [00:00<?, ?B/s]
100%|██████████| 9.91M/9.91M [00:00<00:00, 139MB/s]

  0%|          | 0.00/28.9k [00:00<?, ?B/s]
100%|██████████| 28.9k/28.9k [00:00<00:00, 40.7MB/s]

  0%|          | 0.00/1.65M [00:00<?, ?B/s]
100%|██████████| 1.65M/1.65M [00:00<00:00, 360MB/s]

  0%|          | 0.00/4.54k [00:00<?, ?B/s]
100%|██████████| 4.54k/4.54k [00:00<00:00, 20.4MB/s]
/home/circleci/project/skada/datasets/_mnist_usps.py:72: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.detach().clone() or sourceTensor.detach().clone().requires_grad_(True), rather than torch.tensor(sourceTensor).
  mnist_target = torch.tensor(mnist_dataset.targets)

  0%|          | 0.00/1.83M [00:00<?, ?B/s]
  2%|▏         | 32.8k/1.83M [00:00<00:10, 177kB/s]
  5%|▌         | 98.3k/1.83M [00:00<00:06, 281kB/s]
 11%|█         | 197k/1.83M [00:00<00:04, 393kB/s]
 21%|██▏       | 393k/1.83M [00:00<00:02, 656kB/s]
 43%|████▎     | 786k/1.83M [00:00<00:00, 1.18MB/s]
 86%|████████▌ | 1.57M/1.83M [00:01<00:00, 2.22MB/s]
100%|██████████| 1.83M/1.83M [00:01<00:00, 1.64MB/s]

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        1.6877  2.9544
      2        0.3590  2.9982
      3        0.1214  2.8958
      4        0.0608  2.8929
      5        0.0459  2.8980

0.9196141479099679

Train a DeepCoral model

model = DeepCoral(
    MNISTtoUSPSNet(),
    layer_name="fc1",
    batch_size=128,
    max_epochs=5,
    train_split=False,
    reg=1,
    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/sklearn/utils/deprecation.py:132: FutureWarning: 'force_all_finite' was renamed to 'ensure_all_finite' in 1.6 and will be removed in 1.8.
  warnings.warn(
  epoch    train_loss     dur
-------  ------------  ------
      1        1.6897  5.9604
      2        0.4445  5.8032
      3        0.1602  5.8988
      4        0.0914  5.8009
      5        0.0655  5.8942
/home/circleci/.local/lib/python3.10/site-packages/sklearn/utils/deprecation.py:132: FutureWarning: 'force_all_finite' was renamed to 'ensure_all_finite' in 1.6 and will be removed in 1.8.
  warnings.warn(
/home/circleci/.local/lib/python3.10/site-packages/sklearn/utils/deprecation.py:132: FutureWarning: 'force_all_finite' was renamed to 'ensure_all_finite' in 1.6 and will be removed in 1.8.
  warnings.warn(
/home/circleci/.local/lib/python3.10/site-packages/sklearn/utils/deprecation.py:132: FutureWarning: 'force_all_finite' was renamed to 'ensure_all_finite' in 1.6 and will be removed in 1.8.
  warnings.warn(

0.9196141479099679

Total running time of the script: (0 minutes 51.326 seconds)

Gallery generated by Sphinx-Gallery