[MRG] Tensorflow backend & Benchmarker & Myst_parser

.github/requirements_test_windows.txt

@@ -4,7 +4,7 @@ cython
 matplotlib
 autograd
 pymanopt==0.2.4; python_version <'3'
-pymanopt; python_version >= '3'
+pymanopt==0.2.6rc1; python_version >= '3'
 cvxopt
 scikit-learn
 pytest

README.md

@@ -35,7 +35,7 @@ POT provides the following generic OT solvers (links to examples):
 * [Partial Wasserstein and Gromov-Wasserstein](https://pythonot.github.io/auto_examples/unbalanced-partial/plot_partial_wass_and_gromov.html) (exact [29] and entropic [3]
   formulations).
 * [Sliced Wasserstein](https://pythonot.github.io/auto_examples/sliced-wasserstein/plot_variance.html) [31, 32] and Max-sliced Wasserstein [35] that can be used for gradient flows [36].
-* [Several backends](https://pythonot.github.io/quickstart.html#solving-ot-with-multiple-backends) for easy use of POT with  [Pytorch](https://pytorch.org/)/[jax](https://github.com/google/jax)/[Numpy](https://numpy.org/) arrays.
+* [Several backends](https://pythonot.github.io/quickstart.html#solving-ot-with-multiple-backends) for easy use of POT with  [Pytorch](https://pytorch.org/)/[jax](https://github.com/google/jax)/[Numpy](https://numpy.org/)/[Cupy](https://cupy.dev/)/[Tensorflow](https://www.tensorflow.org/) arrays.
 
 POT provides the following Machine Learning related solvers:
 
@@ -202,12 +202,12 @@ This toolbox benefit a lot from open source research and we would like to thank
 
 * [Gabriel Peyré](http://gpeyre.github.io/) (Wasserstein Barycenters in Matlab)
 * [Mathieu Blondel](https://mblondel.org/) (original implementation smooth OT)
-* [Nicolas Bonneel](http://liris.cnrs.fr/~nbonneel/) ( C++ code for EMD)
+* [Nicolas Bonneel](http://liris.cnrs.fr/~nbonneel/) (C++ code for EMD)
 * [Marco Cuturi](http://marcocuturi.net/) (Sinkhorn Knopp in Matlab/Cuda)
 
 ## Contributions and code of conduct
 
-Every contribution is welcome and should respect the [contribution guidelines](https://pythonot.github.io/contributing.html). Each member of the project is expected to follow the [code of conduct](https://pythonot.github.io/code_of_conduct.html).
+Every contribution is welcome and should respect the [contribution guidelines](.github/CONTRIBUTING.md). Each member of the project is expected to follow the [code of conduct](.github/CODE_OF_CONDUCT.md).
 
 ## Support
 
@@ -217,7 +217,7 @@ You can ask questions and join the development discussion:
 * On the POT [gitter channel](https://gitter.im/PythonOT/community)
 * On the POT [mailing list](https://mail.python.org/mm3/mailman3/lists/pot.python.org/)
 
-You can also post bug reports and feature requests in Github issues. Make sure to read our [guidelines](https://pythonot.github.io/contributing.html) first.
+You can also post bug reports and feature requests in Github issues. Make sure to read our [guidelines](.github/CONTRIBUTING.md) first.
 
 ## References
 

benchmarks/__init__.py

@@ -0,0 +1,5 @@
+from . import benchmark
+from . import sinkhorn_knopp
+from . import emd
+
+__all__= ["benchmark", "sinkhorn_knopp", "emd"]

benchmarks/benchmark.py

@@ -0,0 +1,105 @@
+# /usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from ot.backend import get_backend_list, jax, tf
+import gc
+
+
+def setup_backends():
+    if jax:
+        from jax.config import config
+        config.update("jax_enable_x64", True)
+
+    if tf:
+        from tensorflow.python.ops.numpy_ops import np_config
+        np_config.enable_numpy_behavior()
+
+
+def exec_bench(setup, tested_function, param_list, n_runs, warmup_runs):
+    backend_list = get_backend_list()
+    for i, nx in enumerate(backend_list):
+        if nx.__name__ == "tf" and i < len(backend_list) - 1:
+            # Tensorflow should be the last one to be benchmarked because
+            # as far as I'm aware, there is no way to force it to release
+            # GPU memory. Hence, if any other backend is benchmarked after
+            # Tensorflow and requires the usage of a GPU, it will not have the
+            # full memory available and you may have a GPU Out Of Memory error
+            # even though your GPU can technically hold your tensors in memory.
+            backend_list.pop(i)
+            backend_list.append(nx)
+            break
+
+    inputs = [setup(param) for param in param_list]
+    results = dict()
+    for nx in backend_list:
+        for i in range(len(param_list)):
+            print(nx, param_list[i])
+            args = inputs[i]
+            results_nx = nx._bench(
+                tested_function,
+                *args,
+                n_runs=n_runs,
+                warmup_runs=warmup_runs
+            )
+            gc.collect()
+            results_nx_with_param_in_key = dict()
+            for key in results_nx:
+                new_key = (param_list[i], *key)
+                results_nx_with_param_in_key[new_key] = results_nx[key]
+            results.update(results_nx_with_param_in_key)
+    return results
+
+
+def convert_to_html_table(results, param_name, main_title=None, comments=None):
+    string = "<table>\n"
+    keys = list(results.keys())
+    params, names, devices, bitsizes = zip(*keys)
+
+    devices_names = sorted(list(set(zip(devices, names))))
+    params = sorted(list(set(params)))
+    bitsizes = sorted(list(set(bitsizes)))
+    length = len(devices_names) + 1
+    cpus_cols = list(devices).count("CPU") / len(bitsizes) / len(params)
+    gpus_cols = list(devices).count("GPU") / len(bitsizes) / len(params)
+    assert cpus_cols + gpus_cols == len(devices_names)
+
+    if main_title is not None:
+        string += f'<tr><th align="center" colspan="{length}">{str(main_title)}</th></tr>\n'
+
+    for i, bitsize in enumerate(bitsizes):
+
+        if i != 0:
+            string += f'<tr><td colspan="{length}">&nbsp;</td></tr>\n'
+
+        # make bitsize header
+        text = f"{bitsize} bits"
+        if comments is not None:
+            text += " - "
+            if isinstance(comments, (tuple, list)) and len(comments) == len(bitsizes):
+                text += str(comments[i])
+            else:
+                text += str(comments)
+        string += f'<tr><th align="center">Bitsize</th>'
+        string += f'<th align="center" colspan="{length - 1}">{text}</th></tr>\n'
+
+        # make device header
+        string += f'<tr><th align="center">Device</th>'
+        string += f'<th align="center" colspan="{cpus_cols}">CPU</th>'
+        string += f'<th align="center" colspan="{gpus_cols}">GPU</th></tr>\n'
+
+        # make param_name / backend header
+        string += f'<tr><th align="center">{param_name}</th>'
+        for device, name in devices_names:
+            string += f'<th align="center">{name}</th>'
+        string += "</tr>\n"
+
+        # make results rows
+        for param in params:
+            string += f'<tr><td align="center">{param}</td>'
+            for device, name in devices_names:
+                key = (param, name, device, bitsize)
+                string += f'<td align="center">{results[key]:.4f}</td>'
+            string += "</tr>\n"
+
+    string += "</table>"
+    return string

benchmarks/emd.py

@@ -0,0 +1,40 @@
+# /usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import numpy as np
+import ot
+from .benchmark import (
+    setup_backends,
+    exec_bench,
+    convert_to_html_table
+)
+
+
+def setup(n_samples):
+    rng = np.random.RandomState(789465132)
+    x = rng.randn(n_samples, 2)
+    y = rng.randn(n_samples, 2)
+
+    a = ot.utils.unif(n_samples)
+    M = ot.dist(x, y)
+    return a, M
+
+
+if __name__ == "__main__":
+    n_runs = 100
+    warmup_runs = 10
+    param_list = [50, 100, 500, 1000, 2000, 5000]
+
+    setup_backends()
+    results = exec_bench(
+        setup=setup,
+        tested_function=lambda a, M: ot.emd(a, a, M),
+        param_list=param_list,
+        n_runs=n_runs,
+        warmup_runs=warmup_runs
+    )
+    print(convert_to_html_table(
+        results, 
+        param_name="Sample size",
+        main_title=f"EMD - Averaged on {n_runs} runs"
+    ))

benchmarks/sinkhorn_knopp.py

@@ -0,0 +1,42 @@
+# /usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import numpy as np
+import ot
+from .benchmark import (
+    setup_backends,
+    exec_bench,
+    convert_to_html_table
+)
+
+
+def setup(n_samples):
+    rng = np.random.RandomState(123456789)
+    a = rng.rand(n_samples // 4, 100)
+    b = rng.rand(n_samples, 100)
+
+    wa = ot.unif(n_samples // 4)
+    wb = ot.unif(n_samples)
+
+    M = ot.dist(a.copy(), b.copy())
+    return wa, wb, M
+
+
+if __name__ == "__main__":
+    n_runs = 100
+    warmup_runs = 10
+    param_list = [50, 100, 500, 1000, 2000, 5000]
+
+    setup_backends()
+    results = exec_bench(
+        setup=setup,
+        tested_function=lambda *args: ot.bregman.sinkhorn(*args, reg=1, stopThr=1e-7),
+        param_list=param_list,
+        n_runs=n_runs,
+        warmup_runs=warmup_runs
+    )
+    print(convert_to_html_table(
+        results, 
+        param_name="Sample size",
+        main_title=f"Sinkhorn Knopp - Averaged on {n_runs} runs"
+    ))

docs/requirements.txt

@@ -4,4 +4,4 @@ numpydoc
 memory_profiler
 pillow
 networkx
-m2r2
+myst-parser

docs/requirements_rtd.txt

@@ -3,7 +3,7 @@ numpydoc
 memory_profiler
 pillow
 networkx
-m2r2
+myst-parser
 numpy
 scipy>=1.0
 cython

docs/source/.github/CODE_OF_CONDUCT.rst

@@ -0,0 +1,6 @@
+Code of Conduct
+===============
+
+.. include:: ../../../.github/CODE_OF_CONDUCT.md
+    :parser: myst_parser.sphinx_
+    :start-line: 2

docs/source/.github/CONTRIBUTING.rst

@@ -0,0 +1,6 @@
+Contributing to POT
+===================
+
+.. include:: ../../../.github/CONTRIBUTING.md
+    :parser: myst_parser.sphinx_
+    :start-line: 3

docs/source/conf.py

@@ -69,7 +69,7 @@ def __getattr__(cls, name):
     'sphinx.ext.viewcode',
     'sphinx.ext.napoleon',
     'sphinx_gallery.gen_gallery',
-    'm2r2'
+    'myst_parser'
 ]
 
 autosummary_generate = True

docs/source/index.rst

@@ -17,12 +17,11 @@ Contents
    all
    auto_examples/index
    releases
-   contributing
-   Code of Conduct <code_of_conduct>
-
-.. mdinclude:: ../../README.md
-   :start-line: 2
+   .github/CONTRIBUTING
+   .github/CODE_OF_CONDUCT
 
+.. include:: ../../README.md
+   :parser: myst_parser.sphinx_
 
 
 Indices and tables