diff --git a/tools/python/src/global_optimization.cpp b/tools/python/src/global_optimization.cpp
index f27185c51..53b8cfd05 100644
--- a/tools/python/src/global_optimization.cpp
+++ b/tools/python/src/global_optimization.cpp
@@ -245,6 +245,57 @@ function_evaluation py_function_evaluation(
 
 void bind_global_optimization(py::module& m)
 {
+
+
+    const char* docstring =
+"requires \n\
+    - len(bound1) == len(bound2) == len(is_integer_variable) \n\
+    - for all valid i: bound1[i] != bound2[i] \n\
+    - solver_epsilon >= 0 \n\
+    - f() is a real valued multi-variate function.  It must take scalar real \n\
+      numbers as its arguments and the number of arguments must be len(bound1). \n\
+ensures \n\
+    - This function performs global optimization on the given f() function. \n\
+      The goal is to maximize the following objective function: \n\
+         f(x) \n\
+      subject to the constraints: \n\
+        min(bound1[i],bound2[i]) <= x[i] <= max(bound1[i],bound2[i]) \n\
+        if (is_integer_variable[i]) then x[i] is an integer value (but still \n\
+        represented with float type). \n\
+    - find_max_global() runs until it has called f() num_function_calls times. \n\
+      Then it returns the best x it has found along with the corresponding output \n\
+      of f().  That is, it returns (best_x_seen,f(best_x_seen)).  Here best_x_seen \n\
+      is a list containing the best arguments to f() this function has found. \n\
+    - find_max_global() uses a global optimization method based on a combination of \n\
+      non-parametric global function modeling and quadratic trust region modeling \n\
+      to efficiently find a global maximizer.  It usually does a good job with a \n\
+      relatively small number of calls to f().  For more information on how it \n\
+      works read the documentation for dlib's global_function_search object. \n\
+      However, one notable element is the solver epsilon, which you can adjust. \n\
+ \n\
+      The search procedure will only attempt to find a global maximizer to at most \n\
+      solver_epsilon accuracy.  Once a local maximizer is found to that accuracy \n\
+      the search will focus entirely on finding other maxima elsewhere rather than \n\
+      on further improving the current local optima found so far.  That is, once a \n\
+      local maxima is identified to about solver_epsilon accuracy, the algorithm \n\
+      will spend all its time exploring the function to find other local maxima to \n\
+      investigate.  An epsilon of 0 means it will keep solving until it reaches \n\
+      full floating point precision.  Larger values will cause it to switch to pure \n\
+      global exploration sooner and therefore might be more effective if your \n\
+      objective function has many local maxima and you don't care about a super \n\
+      high precision solution. \n\
+    - Any variables that satisfy the following conditions are optimized on a log-scale: \n\
+        - The lower bound on the variable is > 0 \n\
+        - The ratio of the upper bound to lower bound is > 1000 \n\
+        - The variable is not an integer variable \n\
+      We do this because it's common to optimize machine learning models that have \n\
+      parameters with bounds in a range such as [1e-5 to 1e10] (e.g. the SVM C \n\
+      parameter) and it's much more appropriate to optimize these kinds of \n\
+      variables on a log scale.  So we transform them by applying log() to \n\
+      them and then undo the transform via exp() before invoking the function \n\
+      being optimized.  Therefore, this transformation is invisible to the user \n\
+      supplied functions.  In most cases, it improves the efficiency of the \n\
+      optimizer.";
     /*!
         requires
             - len(bound1) == len(bound2) == len(is_integer_variable)
@@ -258,7 +309,8 @@ void bind_global_optimization(py::module& m)
                  f(x)
               subject to the constraints:
                 min(bound1[i],bound2[i]) <= x[i] <= max(bound1[i],bound2[i])
-                if (is_integer_variable[i]) then x[i] is an integer.
+                if (is_integer_variable[i]) then x[i] is an integer value (but still
+                represented with float type).
             - find_max_global() runs until it has called f() num_function_calls times.
               Then it returns the best x it has found along with the corresponding output
               of f().  That is, it returns (best_x_seen,f(best_x_seen)).  Here best_x_seen
@@ -294,83 +346,26 @@ void bind_global_optimization(py::module& m)
               supplied functions.  In most cases, it improves the efficiency of the
               optimizer.
     !*/
-    {
-    m.def("find_max_global", &py_find_max_global, 
-"requires \n\
-    - len(bound1) == len(bound2) == len(is_integer_variable) \n\
-    - for all valid i: bound1[i] != bound2[i] \n\
-    - solver_epsilon >= 0 \n\
-    - f() is a real valued multi-variate function.  It must take scalar real \n\
-      numbers as its arguments and the number of arguments must be len(bound1). \n\
-ensures \n\
-    - This function performs global optimization on the given f() function. \n\
-      The goal is to maximize the following objective function: \n\
-         f(x) \n\
-      subject to the constraints: \n\
-        min(bound1[i],bound2[i]) <= x[i] <= max(bound1[i],bound2[i]) \n\
-        if (is_integer_variable[i]) then x[i] is an integer. \n\
-    - find_max_global() runs until it has called f() num_function_calls times. \n\
-      Then it returns the best x it has found along with the corresponding output \n\
-      of f().  That is, it returns (best_x_seen,f(best_x_seen)).  Here best_x_seen \n\
-      is a list containing the best arguments to f() this function has found. \n\
-    - find_max_global() uses a global optimization method based on a combination of \n\
-      non-parametric global function modeling and quadratic trust region modeling \n\
-      to efficiently find a global maximizer.  It usually does a good job with a \n\
-      relatively small number of calls to f().  For more information on how it \n\
-      works read the documentation for dlib's global_function_search object. \n\
-      However, one notable element is the solver epsilon, which you can adjust. \n\
- \n\
-      The search procedure will only attempt to find a global maximizer to at most \n\
-      solver_epsilon accuracy.  Once a local maximizer is found to that accuracy \n\
-      the search will focus entirely on finding other maxima elsewhere rather than \n\
-      on further improving the current local optima found so far.  That is, once a \n\
-      local maxima is identified to about solver_epsilon accuracy, the algorithm \n\
-      will spend all its time exploring the function to find other local maxima to \n\
-      investigate.  An epsilon of 0 means it will keep solving until it reaches \n\
-      full floating point precision.  Larger values will cause it to switch to pure \n\
-      global exploration sooner and therefore might be more effective if your \n\
-      objective function has many local maxima and you don't care about a super \n\
-      high precision solution. \n\
-    - Any variables that satisfy the following conditions are optimized on a log-scale: \n\
-        - The lower bound on the variable is > 0 \n\
-        - The ratio of the upper bound to lower bound is > 1000 \n\
-        - The variable is not an integer variable \n\
-      We do this because it's common to optimize machine learning models that have \n\
-      parameters with bounds in a range such as [1e-5 to 1e10] (e.g. the SVM C \n\
-      parameter) and it's much more appropriate to optimize these kinds of \n\
-      variables on a log scale.  So we transform them by applying log() to \n\
-      them and then undo the transform via exp() before invoking the function \n\
-      being optimized.  Therefore, this transformation is invisible to the user \n\
-      supplied functions.  In most cases, it improves the efficiency of the \n\
-      optimizer." 
-        , 
-	py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("is_integer_variable"), py::arg("num_function_calls"), py::arg("solver_epsilon")=0
-    );
-    }
+    m.def("find_max_global", &py_find_max_global, docstring, py::arg("f"),
+        py::arg("bound1"), py::arg("bound2"), py::arg("is_integer_variable"),
+        py::arg("num_function_calls"), py::arg("solver_epsilon")=0);
 
-    {
     m.def("find_max_global", &py_find_max_global2, 
         "This function simply calls the other version of find_max_global() with is_integer_variable set to False for all variables.", 
-	py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("num_function_calls"), py::arg("solver_epsilon")=0
-    );
-    }
+        py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("num_function_calls"),
+        py::arg("solver_epsilon")=0);
 
 
 
-    {
     m.def("find_min_global", &py_find_min_global, 
-      "This function is just like find_max_global(), except it performs minimization rather than maximization." 
-        , 
-	py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("is_integer_variable"), py::arg("num_function_calls"), py::arg("solver_epsilon")=0
-    );
-    }
+      "This function is just like find_max_global(), except it performs minimization rather than maximization.", 
+        py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("is_integer_variable"),
+        py::arg("num_function_calls"), py::arg("solver_epsilon")=0);
 
-    {
     m.def("find_min_global", &py_find_min_global2, 
         "This function simply calls the other version of find_min_global() with is_integer_variable set to False for all variables.", 
-	py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("num_function_calls"), py::arg("solver_epsilon")=0
-    );
-    }
+        py::arg("f"), py::arg("bound1"), py::arg("bound2"), py::arg("num_function_calls"),
+        py::arg("solver_epsilon")=0);
 
     // -------------------------------------------------
     // -------------------------------------------------