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, 133MB/s]

  0%|          | 0.00/28.9k [00:00<?, ?B/s]
100%|██████████| 28.9k/28.9k [00:00<00:00, 65.3MB/s]

  0%|          | 0.00/1.65M [00:00<?, ?B/s]
100%|██████████| 1.65M/1.65M [00:00<00:00, 59.5MB/s]

  0%|          | 0.00/4.54k [00:00<?, ?B/s]
100%|██████████| 4.54k/4.54k [00:00<00:00, 10.0MB/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<00:12, 142kB/s]
  4%|▎         | 65.5k/1.83M [00:00<00:12, 142kB/s]
  5%|▌         | 98.3k/1.83M [00:00<00:12, 142kB/s]
 13%|█▎        | 229k/1.83M [00:00<00:05, 308kB/s]
 21%|██▏       | 393k/1.83M [00:01<00:03, 449kB/s]
 39%|███▉      | 721k/1.83M [00:01<00:01, 776kB/s]
 77%|███████▋  | 1.41M/1.83M [00:01<00:00, 1.48MB/s]
100%|██████████| 1.83M/1.83M [00:01<00:00, 1.11MB/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        1.6884  12.7046
      2        0.3133  8.0979
      3        0.1007  6.6415
      4        0.0520  6.0021
      5        0.0370  5.9950

0.9260450160771704

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)
  epoch    train_loss     dur
-------  ------------  ------
      1        1.6431  9.5111
      2        0.3926  7.5020
      3        0.1329  7.0979
      4        0.0715  7.7970
      5        0.0619  7.5018

0.8906752411575563

Total running time of the script: (1 minutes 29.865 seconds)

Gallery generated by Sphinx-Gallery