CircleCI update of dev docs (2612).

Author: Circle CI

master/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -91,12 +91,15 @@ <h1>Source code for ot.partial</h1><div class="highlight"><pre>
 <span class="sd">&quot;&quot;&quot;</span>
 
 <span class="c1"># Author: Laetitia Chapel &lt;[email protected]&gt;</span>
-<span class="c1"># License: MIT License</span>
+<span class="c1">#             Yikun Bai &lt; [email protected] &gt;</span>
+<span class="c1">#             Cédric Vincent-Cuaz &lt;[email protected]&gt;</span>
 
-<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
-<span class="kn">from</span> <span class="nn">.lp</span> <span class="kn">import</span> <span class="n">emd</span>
-<span class="kn">from</span> <span class="nn">.backend</span> <span class="kn">import</span> <span class="n">get_backend</span>
 <span class="kn">from</span> <span class="nn">.utils</span> <span class="kn">import</span> <span class="n">list_to_array</span>
+<span class="kn">from</span> <span class="nn">.backend</span> <span class="kn">import</span> <span class="n">get_backend</span>
+<span class="kn">from</span> <span class="nn">.lp</span> <span class="kn">import</span> <span class="n">emd</span>
+<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
+
+<span class="c1"># License: MIT License</span>
 
 
 <div class="viewcode-block" id="partial_wasserstein_lagrange">
@@ -685,7 +688,7 @@ <h1>Source code for ot.partial</h1><div class="highlight"><pre>
                          <span class="s2">&quot; equal than min(|a|_1, |b|_1).&quot;</span><span class="p">)</span>
 
     <span class="k">if</span> <span class="n">G0</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
-        <span class="n">G0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">outer</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">q</span><span class="p">)</span>
+        <span class="n">G0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">outer</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">q</span><span class="p">)</span> <span class="o">*</span> <span class="n">m</span> <span class="o">/</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">q</span><span class="p">))</span>  <span class="c1"># make sure |G0|=m, G01_m\leq p, G0.T1_n\leq q.</span>
 
     <span class="n">dim_G_extended</span> <span class="o">=</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">+</span> <span class="n">nb_dummies</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">q</span><span class="p">)</span> <span class="o">+</span> <span class="n">nb_dummies</span><span class="p">)</span>
     <span class="n">q_extended</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">q</span><span class="p">,</span> <span class="p">[(</span><span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">-</span> <span class="n">m</span><span class="p">)</span> <span class="o">/</span> <span class="n">nb_dummies</span><span class="p">]</span> <span class="o">*</span> <span class="n">nb_dummies</span><span class="p">)</span>
@@ -701,7 +704,7 @@ <h1>Source code for ot.partial</h1><div class="highlight"><pre>
 
         <span class="n">Gprev</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">G0</span><span class="p">)</span>
 
-        <span class="n">M</span> <span class="o">=</span> <span class="n">gwgrad_partial</span><span class="p">(</span><span class="n">C1</span><span class="p">,</span> <span class="n">C2</span><span class="p">,</span> <span class="n">G0</span><span class="p">)</span>
+        <span class="n">M</span> <span class="o">=</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="n">gwgrad_partial</span><span class="p">(</span><span class="n">C1</span><span class="p">,</span> <span class="n">C2</span><span class="p">,</span> <span class="n">G0</span><span class="p">)</span>  <span class="c1"># rescaling the gradient with 0.5 for line-search while not changing Gc</span>
         <span class="n">M_emd</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">dim_G_extended</span><span class="p">)</span>
         <span class="n">M_emd</span><span class="p">[:</span><span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">),</span> <span class="p">:</span><span class="nb">len</span><span class="p">(</span><span class="n">q</span><span class="p">)]</span> <span class="o">=</span> <span class="n">M</span>
         <span class="n">M_emd</span><span class="p">[</span><span class="o">-</span><span class="n">nb_dummies</span><span class="p">:,</span> <span class="o">-</span><span class="n">nb_dummies</span><span class="p">:]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">M</span><span class="p">)</span> <span class="o">*</span> <span class="mf">1e2</span>

master/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -195,26 +195,26 @@ Estimating dual variables for entropic OT
 
  .. code-block:: none
 
-    Iter:   0, loss=0.20204949002249403
-    Iter:  10, loss=-19.551107159946092
-    Iter:  20, loss=-32.123839901628024
-    Iter:  30, loss=-36.940664116171
-    Iter:  40, loss=-40.03489446590721
-    Iter:  50, loss=-42.17637976107136
-    Iter:  60, loss=-43.1834917369902
-    Iter:  70, loss=-43.469236138819014
-    Iter:  80, loss=-43.61806696879967
-    Iter:  90, loss=-43.67796282200493
-    Iter: 100, loss=-43.700087076578285
-    Iter: 110, loss=-43.710467877462726
-    Iter: 120, loss=-43.714445212715916
-    Iter: 130, loss=-43.716936716927314
-    Iter: 140, loss=-43.718408156825426
-    Iter: 150, loss=-43.719383886047595
-    Iter: 160, loss=-43.72005046669278
-    Iter: 170, loss=-43.720540500316126
-    Iter: 180, loss=-43.72091116792597
-    Iter: 190, loss=-43.72119758456282
+    Iter:   0, loss=0.20204949002247768
+    Iter:  10, loss=-19.421076011030973
+    Iter:  20, loss=-31.01347922399722
+    Iter:  30, loss=-35.30574692843582
+    Iter:  40, loss=-38.25482934417789
+    Iter:  50, loss=-39.94700713622043
+    Iter:  60, loss=-40.590722404951016
+    Iter:  70, loss=-40.876517772427746
+    Iter:  80, loss=-40.981766342058656
+    Iter:  90, loss=-41.01925620581441
+    Iter: 100, loss=-41.035667717719626
+    Iter: 110, loss=-41.04408524749168
+    Iter: 120, loss=-41.048123660089196
+    Iter: 130, loss=-41.05044871731107
+    Iter: 140, loss=-41.052037008940786
+    Iter: 150, loss=-41.053131804726945
+    Iter: 160, loss=-41.05392342805668
+    Iter: 170, loss=-41.05451081324624
+    Iter: 180, loss=-41.05495492130819
+    Iter: 190, loss=-41.05529685460488
 
 
 
@@ -319,25 +319,25 @@ Estimating dual variables for quadratic OT
  .. code-block:: none
 
     Iter:   0, loss=-0.0018442196020623663
-    Iter:  10, loss=-19.55444372310591
-    Iter:  20, loss=-31.82508719397455
-    Iter:  30, loss=-36.73124069065788
-    Iter:  40, loss=-39.80632209911891
-    Iter:  50, loss=-41.90918504839524
-    Iter:  60, loss=-42.98670159091879
-    Iter:  70, loss=-43.288838093463525
-    Iter:  80, loss=-43.47543632032131
-    Iter:  90, loss=-43.54103654142782
-    Iter: 100, loss=-43.568396593557175
-    Iter: 110, loss=-43.58197663105146
-    Iter: 120, loss=-43.58843119615174
-    Iter: 130, loss=-43.59203350781738
-    Iter: 140, loss=-43.59416513265756
-    Iter: 150, loss=-43.59561976515732
-    Iter: 160, loss=-43.596533431804446
-    Iter: 170, loss=-43.59716892761811
-    Iter: 180, loss=-43.597616524183444
-    Iter: 190, loss=-43.59793393828832
+    Iter:  10, loss=-19.443925220396057
+    Iter:  20, loss=-30.922727653081377
+    Iter:  30, loss=-35.012935936676605
+    Iter:  40, loss=-38.162807293250054
+    Iter:  50, loss=-39.67309868070093
+    Iter:  60, loss=-40.40184169424428
+    Iter:  70, loss=-40.69792460462322
+    Iter:  80, loss=-40.83866091755958
+    Iter:  90, loss=-40.889707794245346
+    Iter: 100, loss=-40.91011324230527
+    Iter: 110, loss=-40.921533554889265
+    Iter: 120, loss=-40.926797175066206
+    Iter: 130, loss=-40.92995805175755
+    Iter: 140, loss=-40.932105252547856
+    Iter: 150, loss=-40.93356100320511
+    Iter: 160, loss=-40.934598491958205
+    Iter: 170, loss=-40.93532662271355
+    Iter: 180, loss=-40.93581813825356
+    Iter: 190, loss=-40.9361241965941
 
 
 
@@ -380,7 +380,7 @@ Plot the estimated quadratic OT plan
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 13.099 seconds)
+   **Total running time of the script:** (0 minutes 9.560 seconds)
 
 
 .. _sphx_glr_download_auto_examples_backends_plot_dual_ot_pytorch.py:

master/_images/sphx_glr_plot_OT_2D_samples_001.png

@@ -395,14 +395,14 @@ classes
     Estimated weights :  [0.29985821 0.18926744 0.51087435]
     True proportions :  [0.5 0.3 0.2]
 
-    <matplotlib.colorbar.Colorbar object at 0x7fb6f1c6b4c0>
+    <matplotlib.colorbar.Colorbar object at 0x7f9c5a94f400>
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 8.867 seconds)
+   **Total running time of the script:** (0 minutes 8.804 seconds)
 
 
 .. _sphx_glr_download_auto_examples_backends_plot_optim_gromov_pytorch.py: