Divergence domain adaptation methods.

This example illustrates the DeepCoral method from [1] on a simple image classification task.

[1]

Baochen Sun and Kate Saenko. Deep coral: Correlation alignment for deep domain adaptation. In ECCV Workshops, 2016.

# 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_train(as_sources=["mnist"], as_targets=["usps"])
X_test, y_test, sample_domain_test = dataset.pack_test(as_targets=["usps"])

Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
Failed to download (trying next):
HTTP Error 403: Forbidden

Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-images-idx3-ubyte.gz to ./datasets/MNIST/raw/train-images-idx3-ubyte.gz

  0%|          | 0/9912422 [00:00<?, ?it/s]
100%|██████████| 9912422/9912422 [00:00<00:00, 135416947.57it/s]
Extracting ./datasets/MNIST/raw/train-images-idx3-ubyte.gz to ./datasets/MNIST/raw

Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
Failed to download (trying next):
HTTP Error 403: Forbidden

Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/train-labels-idx1-ubyte.gz to ./datasets/MNIST/raw/train-labels-idx1-ubyte.gz

  0%|          | 0/28881 [00:00<?, ?it/s]
100%|██████████| 28881/28881 [00:00<00:00, 45591153.11it/s]
Extracting ./datasets/MNIST/raw/train-labels-idx1-ubyte.gz to ./datasets/MNIST/raw

Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
Failed to download (trying next):
HTTP Error 403: Forbidden

Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-images-idx3-ubyte.gz to ./datasets/MNIST/raw/t10k-images-idx3-ubyte.gz

  0%|          | 0/1648877 [00:00<?, ?it/s]
100%|██████████| 1648877/1648877 [00:00<00:00, 124308284.29it/s]
Extracting ./datasets/MNIST/raw/t10k-images-idx3-ubyte.gz to ./datasets/MNIST/raw

Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
Failed to download (trying next):
HTTP Error 403: Forbidden

Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz
Downloading https://ossci-datasets.s3.amazonaws.com/mnist/t10k-labels-idx1-ubyte.gz to ./datasets/MNIST/raw/t10k-labels-idx1-ubyte.gz

  0%|          | 0/4542 [00:00<?, ?it/s]
100%|██████████| 4542/4542 [00:00<00:00, 13834806.66it/s]
Extracting ./datasets/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./datasets/MNIST/raw

/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)
Downloading https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/usps.t.bz2 to ./datasets/usps.t.bz2

  0%|          | 0/1831726 [00:00<?, ?it/s]
  2%|▏         | 32768/1831726 [00:00<00:10, 165759.25it/s]
  4%|▎         | 65536/1831726 [00:00<00:10, 165592.90it/s]
  5%|▌         | 98304/1831726 [00:00<00:10, 165832.75it/s]
 13%|█▎        | 229376/1831726 [00:00<00:04, 361654.36it/s]
 25%|██▌       | 458752/1831726 [00:00<00:02, 649087.63it/s]
 48%|████▊     | 884736/1831726 [00:01<00:00, 1160213.89it/s]
 98%|█████████▊| 1802240/1831726 [00:01<00:00, 2294293.44it/s]
100%|██████████| 1831726/1831726 [00:01<00:00, 1321243.74it/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        1.6599  2.6128
      2        0.4158  3.2110
      3        0.1322  2.9048
      4        0.0760  2.9995
      5        0.0529  2.7021

0.8681672025723473

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        1.4944  4.8805
      2        0.3791  5.0937
      3        0.1755  5.1045
      4        0.1195  5.4045
      5        0.0910  5.6992

0.8617363344051447