.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/domain-adaptation/plot_otda_mapping_colors_images.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_domain-adaptation_plot_otda_mapping_colors_images.py: ===================================================== OT for image color adaptation with mapping estimation ===================================================== OT for domain adaptation with image color adaptation [6] with mapping estimation [8]. [6] Ferradans, S., Papadakis, N., Peyre, G., & Aujol, J. F. (2014). Regularized discrete optimal transport. SIAM Journal on Imaging Sciences, 7(3), 1853-1882. [8] M. Perrot, N. Courty, R. Flamary, A. Habrard, "Mapping estimation for discrete optimal transport", Neural Information Processing Systems (NIPS), 2016. .. GENERATED FROM PYTHON SOURCE LINES 17-48 .. code-block:: Python # Authors: Remi Flamary # Stanislas Chambon # # License: MIT License # sphinx_gallery_thumbnail_number = 3 import os from pathlib import Path import numpy as np from matplotlib import pyplot as plt import ot rng = np.random.RandomState(42) def im2mat(img): """Converts and image to matrix (one pixel per line)""" return img.reshape((img.shape[0] * img.shape[1], img.shape[2])) def mat2im(X, shape): """Converts back a matrix to an image""" return X.reshape(shape) def minmax(img): return np.clip(img, 0, 1) .. GENERATED FROM PYTHON SOURCE LINES 49-51 Generate data ------------- .. GENERATED FROM PYTHON SOURCE LINES 51-71 .. code-block:: Python # Loading images this_file = os.path.realpath('__file__') data_path = os.path.join(Path(this_file).parent.parent.parent, 'data') I1 = plt.imread(os.path.join(data_path, 'ocean_day.jpg')).astype(np.float64) / 256 I2 = plt.imread(os.path.join(data_path, 'ocean_sunset.jpg')).astype(np.float64) / 256 X1 = im2mat(I1) X2 = im2mat(I2) # training samples nb = 500 idx1 = rng.randint(X1.shape[0], size=(nb,)) idx2 = rng.randint(X2.shape[0], size=(nb,)) Xs = X1[idx1, :] Xt = X2[idx2, :] .. GENERATED FROM PYTHON SOURCE LINES 72-74 Domain adaptation for pixel distribution transfer ------------------------------------------------- .. GENERATED FROM PYTHON SOURCE LINES 74-102 .. code-block:: Python # EMDTransport ot_emd = ot.da.EMDTransport() ot_emd.fit(Xs=Xs, Xt=Xt) transp_Xs_emd = ot_emd.transform(Xs=X1) Image_emd = minmax(mat2im(transp_Xs_emd, I1.shape)) # SinkhornTransport ot_sinkhorn = ot.da.SinkhornTransport(reg_e=1e-1) ot_sinkhorn.fit(Xs=Xs, Xt=Xt) transp_Xs_sinkhorn = ot_sinkhorn.transform(Xs=X1) Image_sinkhorn = minmax(mat2im(transp_Xs_sinkhorn, I1.shape)) ot_mapping_linear = ot.da.MappingTransport( mu=1e0, eta=1e-8, bias=True, max_iter=20, verbose=True) ot_mapping_linear.fit(Xs=Xs, Xt=Xt) X1tl = ot_mapping_linear.transform(Xs=X1) Image_mapping_linear = minmax(mat2im(X1tl, I1.shape)) ot_mapping_gaussian = ot.da.MappingTransport( mu=1e0, eta=1e-2, sigma=1, bias=False, max_iter=10, verbose=True) ot_mapping_gaussian.fit(Xs=Xs, Xt=Xt) X1tn = ot_mapping_gaussian.transform(Xs=X1) # use the estimated mapping Image_mapping_gaussian = minmax(mat2im(X1tn, I1.shape)) .. rst-class:: sphx-glr-script-out .. code-block:: none It. |Loss |Delta loss -------------------------------- 0|1.797245e+02|0.000000e+00 1|1.758014e+02|-2.182822e-02 2|1.757026e+02|-5.620752e-04 3|1.756521e+02|-2.875691e-04 4|1.756218e+02|-1.725224e-04 5|1.756015e+02|-1.153553e-04 6|1.755868e+02|-8.348118e-05 7|1.755759e+02|-6.234582e-05 8|1.755673e+02|-4.893582e-05 9|1.755604e+02|-3.942771e-05 10|1.755547e+02|-3.206000e-05 11|1.755500e+02|-2.695056e-05 12|1.755460e+02|-2.307154e-05 13|1.755426e+02|-1.944208e-05 14|1.755395e+02|-1.715960e-05 15|1.755369e+02|-1.515613e-05 16|1.755345e+02|-1.367864e-05 17|1.755324e+02|-1.197885e-05 18|1.755305e+02|-1.071067e-05 19|1.755303e+02|-9.898122e-07 It. |Loss |Delta loss -------------------------------- 0|1.842001e+02|0.000000e+00 1|1.780145e+02|-3.358084e-02 2|1.778490e+02|-9.296544e-04 3|1.777841e+02|-3.648247e-04 4|1.777495e+02|-1.948923e-04 5|1.777284e+02|-1.184075e-04 6|1.777135e+02|-8.396988e-05 7|1.777027e+02|-6.059322e-05 8|1.776945e+02|-4.619816e-05 9|1.776880e+02|-3.672789e-05 10|1.776827e+02|-2.971430e-05 .. GENERATED FROM PYTHON SOURCE LINES 103-105 Plot original images -------------------- .. GENERATED FROM PYTHON SOURCE LINES 105-119 .. code-block:: Python plt.figure(1, figsize=(6.4, 3)) plt.subplot(1, 2, 1) plt.imshow(I1) plt.axis('off') plt.title('Image 1') plt.subplot(1, 2, 2) plt.imshow(I2) plt.axis('off') plt.title('Image 2') plt.tight_layout() .. image-sg:: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_001.png :alt: Image 1, Image 2 :srcset: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_001.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 120-122 Plot pixel values distribution ------------------------------ .. GENERATED FROM PYTHON SOURCE LINES 122-141 .. code-block:: Python plt.figure(2, figsize=(6.4, 5)) plt.subplot(1, 2, 1) plt.scatter(Xs[:, 0], Xs[:, 2], c=Xs) plt.axis([0, 1, 0, 1]) plt.xlabel('Red') plt.ylabel('Blue') plt.title('Image 1') plt.subplot(1, 2, 2) plt.scatter(Xt[:, 0], Xt[:, 2], c=Xt) plt.axis([0, 1, 0, 1]) plt.xlabel('Red') plt.ylabel('Blue') plt.title('Image 2') plt.tight_layout() .. image-sg:: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_002.png :alt: Image 1, Image 2 :srcset: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_002.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 142-144 Plot transformed images ----------------------- .. GENERATED FROM PYTHON SOURCE LINES 144-179 .. code-block:: Python plt.figure(2, figsize=(10, 5)) plt.subplot(2, 3, 1) plt.imshow(I1) plt.axis('off') plt.title('Im. 1') plt.subplot(2, 3, 4) plt.imshow(I2) plt.axis('off') plt.title('Im. 2') plt.subplot(2, 3, 2) plt.imshow(Image_emd) plt.axis('off') plt.title('EmdTransport') plt.subplot(2, 3, 5) plt.imshow(Image_sinkhorn) plt.axis('off') plt.title('SinkhornTransport') plt.subplot(2, 3, 3) plt.imshow(Image_mapping_linear) plt.axis('off') plt.title('MappingTransport (linear)') plt.subplot(2, 3, 6) plt.imshow(Image_mapping_gaussian) plt.axis('off') plt.title('MappingTransport (gaussian)') plt.tight_layout() plt.show() .. image-sg:: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_003.png :alt: Im. 1, Im. 2, EmdTransport, SinkhornTransport, MappingTransport (linear), MappingTransport (gaussian) :srcset: /auto_examples/domain-adaptation/images/sphx_glr_plot_otda_mapping_colors_images_003.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 46.389 seconds) .. _sphx_glr_download_auto_examples_domain-adaptation_plot_otda_mapping_colors_images.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_otda_mapping_colors_images.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_otda_mapping_colors_images.py ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_