auto: Rebuild docs.

Author: github-actions

_examples/Amortized_Point_Estimation.html

@@ -398,7 +398,7 @@ <h1>Source code for bayesflow.amortizers</h1><div class="highlight"><pre>
 <span class="kn">from</span> <span class="nn">bayesflow.default_settings</span> <span class="kn">import</span> <span class="n">DEFAULT_KEYS</span>
 <span class="kn">from</span> <span class="nn">bayesflow.exceptions</span> <span class="kn">import</span> <span class="n">ConfigurationError</span><span class="p">,</span> <span class="n">SummaryStatsError</span>
 <span class="kn">from</span> <span class="nn">bayesflow.helper_functions</span> <span class="kn">import</span> <span class="n">check_tensor_sanity</span>
-<span class="kn">from</span> <span class="nn">bayesflow.losses</span> <span class="kn">import</span> <span class="n">log_loss</span><span class="p">,</span> <span class="n">mmd_summary_space</span>
+<span class="kn">from</span> <span class="nn">bayesflow.losses</span> <span class="kn">import</span> <span class="n">log_loss</span><span class="p">,</span> <span class="n">mmd_summary_space</span><span class="p">,</span> <span class="n">norm_diff</span>
 <span class="kn">from</span> <span class="nn">bayesflow.networks</span> <span class="kn">import</span> <span class="n">EvidentialNetwork</span>
 
 
@@ -820,7 +820,7 @@ <h1>Source code for bayesflow.amortizers</h1><div class="highlight"><pre>
         <span class="k">elif</span> <span class="n">direct_conditions</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
             <span class="n">full_cond</span> <span class="o">=</span> <span class="n">direct_conditions</span>
         <span class="k">else</span><span class="p">:</span>
-            <span class="k">raise</span> <span class="n">SummaryStatsError</span><span class="p">(</span><span class="s2">&quot;Could not concatenarte or determine conditioning inputs...&quot;</span><span class="p">)</span>
+            <span class="k">raise</span> <span class="n">SummaryStatsError</span><span class="p">(</span><span class="s2">&quot;Could not concatenate or determine conditioning inputs...&quot;</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">sum_condition</span><span class="p">,</span> <span class="n">full_cond</span>
 
     <span class="k">def</span> <span class="nf">_determine_latent_dist</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">latent_dist</span><span class="p">):</span>
@@ -1849,7 +1849,7 @@ <h1>Source code for bayesflow.amortizers</h1><div class="highlight"><pre>
 <span class="sd">        &quot;&quot;&quot;</span>
 
         <span class="n">net_out</span> <span class="o">=</span> <span class="bp">self</span><span class="p">(</span><span class="n">input_dict</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
-        <span class="n">loss</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">reduce_mean</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">loss_fn</span><span class="p">(</span><span class="n">net_out</span> <span class="o">-</span> <span class="n">input_dict</span><span class="p">[</span><span class="n">DEFAULT_KEYS</span><span class="p">[</span><span class="s2">&quot;parameters&quot;</span><span class="p">]]))</span>
+        <span class="n">loss</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">reduce_mean</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">loss_fn</span><span class="p">(</span><span class="n">net_out</span><span class="p">,</span> <span class="n">input_dict</span><span class="p">[</span><span class="n">DEFAULT_KEYS</span><span class="p">[</span><span class="s2">&quot;parameters&quot;</span><span class="p">]]))</span>
         <span class="k">return</span> <span class="n">loss</span></div>
 
 
@@ -1879,7 +1879,7 @@ <h1>Source code for bayesflow.amortizers</h1><div class="highlight"><pre>
         <span class="c1"># In case of user-provided loss, override norm order</span>
         <span class="k">if</span> <span class="n">loss_fun</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
             <span class="k">return</span> <span class="n">loss_fun</span>
-        <span class="k">return</span> <span class="n">partial</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">norm</span><span class="p">,</span> <span class="nb">ord</span><span class="o">=</span><span class="n">norm_ord</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></div>
+        <span class="k">return</span> <span class="n">partial</span><span class="p">(</span><span class="n">norm_diff</span><span class="p">,</span> <span class="nb">ord</span><span class="o">=</span><span class="n">norm_ord</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></div>
 
 </pre></div>
 

_images/7c228379d7d9ad4537c889f143b4716bba242ac205598e27d44c41f2fecf5926.png

@@ -739,7 +739,7 @@ <h1>Source code for bayesflow.helper_networks</h1><div class="highlight"><pre>
 
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
 
-        <span class="c1"># Initialize scale and bias with zeros and ones if no batch for initalization was provided.</span>
+        <span class="c1"># Initialize scale and bias with zeros and ones if no batch for initialization was provided.</span>
         <span class="k">if</span> <span class="n">act_norm_init</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">scale</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">Variable</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="n">latent_dim</span><span class="p">,)),</span> <span class="n">trainable</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s2">&quot;act_norm_scale&quot;</span><span class="p">)</span>
 
@@ -1037,7 +1037,15 @@ <h1>Source code for bayesflow.helper_networks</h1><div class="highlight"><pre>
 <div class="viewcode-block" id="ConfigurableMLP.__init__">
 <a class="viewcode-back" href="../../api/bayesflow.helper_networks.html#bayesflow.helper_networks.ConfigurableMLP.__init__">[docs]</a>
     <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
-        <span class="bp">self</span><span class="p">,</span> <span class="n">input_dim</span><span class="p">,</span> <span class="n">hidden_dim</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">num_hidden</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="s2">&quot;relu&quot;</span><span class="p">,</span> <span class="n">residual</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">dropout_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
+        <span class="bp">self</span><span class="p">,</span>
+        <span class="n">input_dim</span><span class="p">,</span>
+        <span class="n">hidden_dim</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span>
+        <span class="n">output_dim</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+        <span class="n">num_hidden</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span>
+        <span class="n">activation</span><span class="o">=</span><span class="s2">&quot;relu&quot;</span><span class="p">,</span>
+        <span class="n">residual</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+        <span class="n">dropout_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span>
+        <span class="o">**</span><span class="n">kwargs</span><span class="p">,</span>
     <span class="p">):</span>
 <span class="w">        </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">        Creates an instance of a flexible and simple MLP with optional residual connections and dropout.</span>
@@ -1048,6 +1056,8 @@ <h1>Source code for bayesflow.helper_networks</h1><div class="highlight"><pre>
 <span class="sd">            The input dimensionality</span>
 <span class="sd">        hidden_dim     : int, optional, default: 512</span>
 <span class="sd">            The dimensionality of the hidden layers</span>
+<span class="sd">        output_dim     : int, optional, default: None</span>
+<span class="sd">            The output dimensionality. If None is passed, `output_dim` is set to `input_dim`</span>
 <span class="sd">        num_hidden     : int, optional, default: 2</span>
 <span class="sd">            The number of hidden layers (minimum: 1)</span>
 <span class="sd">        activation     : string, optional, default: &#39;relu&#39;</span>
@@ -1061,6 +1071,7 @@ <h1>Source code for bayesflow.helper_networks</h1><div class="highlight"><pre>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">input_dim</span> <span class="o">=</span> <span class="n">input_dim</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">output_dim</span> <span class="o">=</span> <span class="n">input_dim</span> <span class="k">if</span> <span class="n">output_dim</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">output_dim</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
             <span class="p">[</span><span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="n">hidden_dim</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="n">activation</span><span class="p">),</span> <span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="n">dropout_rate</span><span class="p">)]</span>
         <span class="p">)</span>
@@ -1073,7 +1084,7 @@ <h1>Source code for bayesflow.helper_networks</h1><div class="highlight"><pre>
                     <span class="n">dropout_rate</span><span class="o">=</span><span class="n">dropout_rate</span><span class="p">,</span>
                 <span class="p">)</span>
             <span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="n">input_dim</span><span class="p">))</span></div>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">output_dim</span><span class="p">))</span></div>
 
 
 <div class="viewcode-block" id="ConfigurableMLP.call">

_images/9126f83d6ddfb5cf7a1cdedeb7766d680f2db88047cdd80d13b3837da9023efb.png

@@ -566,6 +566,26 @@ <h1>Source code for bayesflow.losses</h1><div class="highlight"><pre>
     <span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="n">tf</span><span class="o">.</span><span class="n">reduce_mean</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">reduce_sum</span><span class="p">(</span><span class="n">model_indices</span> <span class="o">*</span> <span class="n">tf</span><span class="o">.</span><span class="n">math</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">preds</span><span class="p">),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
     <span class="k">return</span> <span class="n">loss</span></div>
 
+
+
+<div class="viewcode-block" id="norm_diff">
+<a class="viewcode-back" href="../../api/bayesflow.losses.html#bayesflow.losses.norm_diff">[docs]</a>
+<span class="k">def</span> <span class="nf">norm_diff</span><span class="p">(</span><span class="n">tensor_a</span><span class="p">,</span> <span class="n">tensor_b</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="nb">ord</span><span class="o">=</span><span class="s1">&#39;euclidean&#39;</span><span class="p">):</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
+<span class="sd">    Wrapper around tf.norm that computes the norm of the difference between two tensors along the specified axis.</span>
+
+<span class="sd">    Parameters</span>
+<span class="sd">    ----------</span>
+<span class="sd">    tensor_a : A Tensor.</span>
+<span class="sd">    tensor_b : A Tensor. Must be the same shape as tensor_a.</span>
+<span class="sd">    axis     : Any or None</span>
+<span class="sd">        Axis along which to compute the norm of the difference. Default is None.</span>
+<span class="sd">    ord      : int or str</span>
+<span class="sd">        Order of the norm. Supports &#39;euclidean&#39; and other norms supported by tf.norm. Default is &#39;euclidean&#39;.</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="n">difference</span> <span class="o">=</span> <span class="n">tensor_a</span> <span class="o">-</span> <span class="n">tensor_b</span>
+    <span class="k">return</span> <span class="n">tf</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="n">difference</span><span class="p">,</span> <span class="nb">ord</span><span class="o">=</span><span class="nb">ord</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">)</span></div>
+
 </pre></div>
 
                 </article>