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%|          | 0.00/9.91M [00:00<?, ?B/s]
100%|██████████| 9.91M/9.91M [00:00<00:00, 130MB/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%|          | 0.00/28.9k [00:00<?, ?B/s]
100%|██████████| 28.9k/28.9k [00:00<00:00, 28.8MB/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%|          | 0.00/1.65M [00:00<?, ?B/s]
100%|██████████| 1.65M/1.65M [00:00<00:00, 236MB/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%|          | 0.00/4.54k [00:00<?, ?B/s]
100%|██████████| 4.54k/4.54k [00:00<00:00, 14.7MB/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%|          | 0.00/1.83M [00:00<?, ?B/s]
  2%|▏         | 32.8k/1.83M [00:00<00:11, 154kB/s]
  4%|▎         | 65.5k/1.83M [00:00<00:11, 154kB/s]
  7%|▋         | 131k/1.83M [00:00<00:07, 224kB/s]
 13%|█▎        | 229k/1.83M [00:00<00:05, 318kB/s]
 25%|██▌       | 459k/1.83M [00:01<00:02, 590kB/s]
 45%|████▍     | 819k/1.83M [00:01<00:01, 954kB/s]
 91%|█████████ | 1.67M/1.83M [00:01<00:00, 1.96MB/s]
100%|██████████| 1.83M/1.83M [00:01<00:00, 1.23MB/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        1.4748  2.9508
      2        0.3692  2.7973
      3        0.1471  2.7036
      4        0.0838  2.5985
      5        0.0558  2.5005

0.887459807073955

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        1.5530  6.7772
      2        0.2746  6.5688
      3        0.1101  6.4290
      4        0.0836  6.8994
      5        0.0712  6.8981

0.8778135048231511