updated docs

docs/docs/main_menu.xml

@@ -208,6 +208,14 @@
                   <name>Deep Learning Inception</name>
                   <link>dnn_inception_ex.cpp.html</link>
                </item>
+               <item>
+                  <name>Deep Metric Learning Introduction</name>
+                  <link>dnn_metric_learning_ex.cpp.html</link>
+               </item>
+               <item>
+                  <name>Deep Metric Learning on Images</name>
+                  <link>dnn_metric_learning_on_images_ex.cpp.html</link>
+               </item>
                <item>
                   <name>Deep Learning Face Detection</name>
                   <link>dnn_mmod_face_detection_ex.cpp.html</link>

docs/docs/ml.xml

@@ -230,6 +230,14 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
                   <name>loss_mmod</name>
                   <link>#loss_mmod_</link>
                </item>
+               <item>
+                  <name>loss_metric</name>
+                  <link>#loss_metric_</link>
+               </item>
+               <item>
+                  <name>loss_mean_squared_</name>
+                  <link>#loss_mean_squared_</link>
+               </item>
             </sub>
          </item>
          <item nolink="true">
@@ -451,6 +459,8 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
             <example>dnn_mmod_ex.cpp.html</example>
             <example>dnn_mmod_face_detection_ex.cpp.html</example>
             <example>dnn_mmod_dog_hipsterizer.cpp.html</example>
+            <example>dnn_metric_learning_ex.cpp.html</example>
+            <example>dnn_metric_learning_on_images_ex.cpp.html</example>
          </examples>
       </component>
 
@@ -475,6 +485,8 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
             <example>dnn_imagenet_ex.cpp.html</example>
             <example>dnn_imagenet_train_ex.cpp.html</example>
             <example>dnn_mmod_ex.cpp.html</example>
+            <example>dnn_metric_learning_ex.cpp.html</example>
+            <example>dnn_metric_learning_on_images_ex.cpp.html</example>
          </examples>
       </component>
 
@@ -495,6 +507,8 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
             <example>dnn_imagenet_ex.cpp.html</example>
             <example>dnn_imagenet_train_ex.cpp.html</example>
             <example>dnn_mmod_ex.cpp.html</example>
+            <example>dnn_metric_learning_ex.cpp.html</example>
+            <example>dnn_metric_learning_on_images_ex.cpp.html</example>
             <example>dnn_mmod_face_detection_ex.cpp.html</example>
             <example>dnn_mmod_dog_hipsterizer.cpp.html</example>
          </examples>
@@ -656,11 +670,6 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
          <file>dlib/dnn.h</file>
          <spec_file link="true">dlib/dnn/loss_abstract.h</spec_file>
          <description>
-            This input layer works with RGB images of type <tt>matrix&lt;rgb_pixel&gt;</tt>.  It is
-            identical to <a href="#input_rgb_image">input_rgb_image</a> except that it
-            outputs a tensor containing a <a href="imaging.html#create_tiled_pyramid">tiled image pyramid</a> 
-            of each input image rather than a simple copy of each image.  
-
             This object is a <a href="dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_">loss layer</a> 
             for a deep neural network.  In particular, it implements the Max Margin Object Detection 
             loss defined in the paper:
@@ -676,6 +685,37 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
          </examples>
       </component>
       
+   <!-- ************************************************************************* -->
+
+      <component>
+         <name>loss_metric_</name>
+         <file>dlib/dnn.h</file>
+         <spec_file link="true">dlib/dnn/loss_abstract.h</spec_file>
+         <description>
+            This object is a <a href="dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_">loss layer</a> 
+            for a deep neural network.   In particular, it allows you to learn to map objects
+            into a vector space where objects sharing the same class label are close to
+            each other, while objects with different labels are far apart.   
+         </description>
+         <examples>
+            <example>dnn_metric_learning_ex.cpp.html</example>
+            <example>dnn_metric_learning_on_images_ex.cpp.html</example>
+         </examples>
+      </component>
+
+   <!-- ************************************************************************* -->
+
+      <component>
+         <name>loss_mean_squared_</name>
+         <file>dlib/dnn.h</file>
+         <spec_file link="true">dlib/dnn/loss_abstract.h</spec_file>
+         <description>
+            This object is a <a href="dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_">loss layer</a> 
+            for a deep neural network. In particular, it implements the mean squared loss, which is
+            appropriate for regression problems.
+         </description>
+      </component>
+
    <!-- ************************************************************************* -->
 
       <component>

docs/docs/term_index.xml

@@ -125,6 +125,8 @@
          <term file="dlib/dnn/loss_abstract.h.html" name="loss_binary_hinge_" include="dlib/dnn.h"/>
          <term file="dlib/dnn/loss_abstract.h.html" name="loss_binary_log_" include="dlib/dnn.h"/>
          <term file="dlib/dnn/loss_abstract.h.html" name="loss_multiclass_log_" include="dlib/dnn.h"/>
+         <term file="ml.html" name="loss_metric_" include="dlib/dnn.h"/>
+         <term file="ml.html" name="loss_mean_squared_" include="dlib/dnn.h"/>
          <term file="ml.html" name="loss_mmod_" include="dlib/dnn.h"/>
          <term file="dlib/dnn/loss_abstract.h.html" name="mmod_options" include="dlib/dnn.h"/>