diff --git a/src/TensorFlowNET.Core/Functions/TapeGradientFunctions.cs b/src/TensorFlowNET.Core/Functions/TapeGradientFunctions.cs
index 89f87c62..45b0de26 100644
--- a/src/TensorFlowNET.Core/Functions/TapeGradientFunctions.cs
+++ b/src/TensorFlowNET.Core/Functions/TapeGradientFunctions.cs
@@ -97,7 +97,8 @@ namespace Tensorflow.Functions
                 .ToArray();
             foreach(var capture in captures_from_forward)
             {
-                _func_graph.Outputs.Add(capture);
+                if (!_func_graph.Outputs.Contains(capture))
+                    _func_graph.Outputs.Add(capture);
             }
 
             var forward_function_name = $"{_FORWARD_PREFIX}_{ops.uid()}";
diff --git a/src/TensorFlowNet.Benchmarks/Leak/GpuLeakByCNN.cs b/src/TensorFlowNet.Benchmarks/Leak/GpuLeakByCNN.cs
index aec309a9..b581e590 100644
--- a/src/TensorFlowNet.Benchmarks/Leak/GpuLeakByCNN.cs
+++ b/src/TensorFlowNet.Benchmarks/Leak/GpuLeakByCNN.cs
@@ -6,14 +6,15 @@ using NumSharp;
 using Tensorflow.Keras;
 using static Tensorflow.Binding;
 using static Tensorflow.KerasApi;
+using BenchmarkDotNet.Attributes;
 
 namespace Tensorflow.Benchmark.Leak
 {
-    class GpuLeakByCNN
+    public class GpuLeakByCNN
     {
         protected static LayersApi layers = new LayersApi();
-
-        public static void Test()
+        [Benchmark]
+        public void Run()
         {
             int num = 50, width = 64, height = 64;
             // if width = 128, height = 128, the exception occurs faster
@@ -29,16 +30,16 @@ namespace Tensorflow.Benchmark.Leak
 
             tf.enable_eager_execution();
 
-            var inputss = keras.Input((height, width, 3));
+            var inputs = keras.Input((height, width, 3));
 
-            var inputs = layers.Conv2D(32, (3, 3), activation: keras.activations.Relu).Apply(inputss);
-            inputs = layers.MaxPooling2D((2, 2)).Apply(inputs);
+            var layer = layers.Conv2D(32, (3, 3), activation: keras.activations.Relu).Apply(inputs);
+            layer = layers.MaxPooling2D((2, 2)).Apply(layer);
 
-            inputs = layers.Flatten().Apply(inputs);
+            layer = layers.Flatten().Apply(layer);
 
-            var outputs = layers.Dense(10).Apply(inputs);
+            var outputs = layers.Dense(10).Apply(layer);
 
-            var model = keras.Model(inputss, outputs, "gpuleak");
+            var model = keras.Model(inputs, outputs, "gpuleak");
 
             model.summary();
 
@@ -46,7 +47,7 @@ namespace Tensorflow.Benchmark.Leak
              optimizer: keras.optimizers.RMSprop(),
              metrics: new[] { "accuracy" });
 
-            model.fit(inputImages, outLables, epochs: 200);
+            model.fit(inputImages, outLables, batch_size: 1, epochs: 200);
         }
     }
 }
diff --git a/src/TensorFlowNet.Benchmarks/Program.cs b/src/TensorFlowNet.Benchmarks/Program.cs
index 16269080..1894b1a8 100644
--- a/src/TensorFlowNet.Benchmarks/Program.cs
+++ b/src/TensorFlowNet.Benchmarks/Program.cs
@@ -2,6 +2,7 @@
 using BenchmarkDotNet.Running;
 using System;
 using System.Reflection;
+using Tensorflow.Benchmark.Leak;
 
 namespace TensorFlowBenchmark
 {
@@ -9,6 +10,8 @@ namespace TensorFlowBenchmark
     {
         static void Main(string[] args)
         {
+            new GpuLeakByCNN().Run();
+
             if (args?.Length > 0)
             {
                 for (int i = 0; i < args.Length; i++)
diff --git a/src/TensorFlowNet.Benchmarks/Tensorflow.Benchmark.csproj b/src/TensorFlowNet.Benchmarks/Tensorflow.Benchmark.csproj
index 9069f2ec..1160fa4f 100644
--- a/src/TensorFlowNet.Benchmarks/Tensorflow.Benchmark.csproj
+++ b/src/TensorFlowNet.Benchmarks/Tensorflow.Benchmark.csproj
@@ -23,13 +23,19 @@
     <AllowUnsafeBlocks>true</AllowUnsafeBlocks>
   </PropertyGroup>
 
+  <ItemGroup>
+    <Compile Remove="BenchmarkDotNet.Artifacts\**" />
+    <EmbeddedResource Remove="BenchmarkDotNet.Artifacts\**" />
+    <None Remove="BenchmarkDotNet.Artifacts\**" />
+  </ItemGroup>
+
   <ItemGroup>
     <None Remove="tensorflow.dll" />
   </ItemGroup>
 
   <ItemGroup>
     <PackageReference Include="BenchmarkDotNet" Version="0.12.1" />
-    <PackageReference Include="SciSharp.TensorFlow.Redist" Version="2.3.1" />
+    <PackageReference Include="SciSharp.TensorFlow.Redist-Windows-GPU" Version="2.3.1" />
   </ItemGroup>
 
   <ItemGroup>