diff --git a/libavfilter/dnn/dnn_backend_native_layer_mathbinary.c b/libavfilter/dnn/dnn_backend_native_layer_mathbinary.c
index 222941e952047..c32a0427884a8 100644
--- a/libavfilter/dnn/dnn_backend_native_layer_mathbinary.c
+++ b/libavfilter/dnn/dnn_backend_native_layer_mathbinary.c
@@ -133,6 +133,23 @@ int dnn_execute_layer_math_binary(DnnOperand *operands, const int32_t *input_ope
             }
         }
         return 0;
+    case DMBO_REALDIV:
+        if (params->input0_broadcast) {
+            for (int i = 0; i < dims_count; ++i) {
+                dst[i] = params->v / src[i];
+            }
+        } else if (params->input1_broadcast) {
+            for (int i = 0; i < dims_count; ++i) {
+                dst[i] = src[i] / params->v;
+            }
+        } else {
+            const DnnOperand *input1 = &operands[input_operand_indexes[1]];
+            const float *src1 = input1->data;
+            for (int i = 0; i < dims_count; ++i) {
+                dst[i] = src[i] / src1[i];
+            }
+        }
+        return 0;
     default:
         return -1;
     }
diff --git a/libavfilter/dnn/dnn_backend_native_layer_mathbinary.h b/libavfilter/dnn/dnn_backend_native_layer_mathbinary.h
index d58b48c7471b3..2ffbb66eebcdb 100644
--- a/libavfilter/dnn/dnn_backend_native_layer_mathbinary.h
+++ b/libavfilter/dnn/dnn_backend_native_layer_mathbinary.h
@@ -34,6 +34,7 @@ typedef enum {
     DMBO_SUB = 0,
     DMBO_ADD = 1,
     DMBO_MUL = 2,
+    DMBO_REALDIV = 3,
     DMBO_COUNT
 } DNNMathBinaryOperation;
 
diff --git a/tools/python/convert_from_tensorflow.py b/tools/python/convert_from_tensorflow.py
index dc3b4e381d4f1..a0fdad25b7d5d 100644
--- a/tools/python/convert_from_tensorflow.py
+++ b/tools/python/convert_from_tensorflow.py
@@ -71,7 +71,7 @@ def __init__(self, graph_def, nodes, outfile, dump4tb):
         self.conv2d_scope_names = set()
         self.conv2d_scopename_inputname_dict = {}
         self.op2code = {'Conv2D':1, 'DepthToSpace':2, 'MirrorPad':3, 'Maximum':4, 'MathBinary':5}
-        self.mathbin2code = {'Sub':0, 'Add':1, 'Mul':2}
+        self.mathbin2code = {'Sub':0, 'Add':1, 'Mul':2, 'RealDiv':3}
         self.mirrorpad_mode = {'CONSTANT':0, 'REFLECT':1, 'SYMMETRIC':2}
         self.name_operand_dict = {}
 
@@ -311,7 +311,8 @@ def dump_layers_to_file(self, f):
                 self.dump_mathbinary_to_file(node, f)
             elif node.op == 'Mul':
                 self.dump_mathbinary_to_file(node, f)
-
+            elif node.op == 'RealDiv':
+                self.dump_mathbinary_to_file(node, f)
 
     def dump_operands_to_file(self, f):
             operands = sorted(self.name_operand_dict.values())
diff --git a/tools/python/convert_header.py b/tools/python/convert_header.py
index 87899fe72c6a5..75d1ce803c535 100644
--- a/tools/python/convert_header.py
+++ b/tools/python/convert_header.py
@@ -23,4 +23,4 @@
 major = 1
 
 # increase minor when we don't have to re-convert the model file
-minor = 3
+minor = 4