diff --git a/src/TensorFlowNET.Core/APIs/tf.random.cs b/src/TensorFlowNET.Core/APIs/tf.random.cs
index c3d05c13..877c52ac 100644
--- a/src/TensorFlowNET.Core/APIs/tf.random.cs
+++ b/src/TensorFlowNET.Core/APIs/tf.random.cs
@@ -62,6 +62,19 @@ namespace Tensorflow
                 int? seed = null,
                 string name = null,
                 TF_DataType output_dtype = TF_DataType.DtInvalid) => random_ops.multinomial(logits, num_samples, seed: seed, name: name, output_dtype: output_dtype);
+
+            public Tensor uniform(TensorShape shape,
+                float minval = 0,
+                float maxval = 1,
+                TF_DataType dtype = TF_DataType.TF_FLOAT,
+                int? seed = null,
+                string name = null)
+            {
+                if (dtype.is_integer())
+                    return random_ops.random_uniform_int(shape, (int)minval, (int)maxval, dtype, seed, name);
+                else
+                    return random_ops.random_uniform(shape, minval, maxval, dtype, seed, name);
+            }
         }
 
         public Tensor random_uniform(TensorShape shape,
@@ -70,16 +83,7 @@ namespace Tensorflow
             TF_DataType dtype = TF_DataType.TF_FLOAT,
             int? seed = null,
             string name = null)
-        {
-            if (dtype.is_integer())
-            {
-                return random_ops.random_uniform_int(shape, (int)minval, (int)maxval, dtype, seed, name);
-            }
-            else
-            {
-                return random_ops.random_uniform(shape, minval, maxval, dtype, seed, name);
-            }
-        }
+            => random.uniform(shape, minval: minval, maxval: maxval, dtype: dtype, seed: seed, name: name);
 
         public Tensor truncated_normal(TensorShape shape,
             float mean = 0.0f,
diff --git a/src/TensorFlowNET.Core/Keras/ArgsDefinition/Preprocessing/ResizingArgs.cs b/src/TensorFlowNET.Core/Keras/ArgsDefinition/Preprocessing/ResizingArgs.cs
new file mode 100644
index 00000000..bb6d9277
--- /dev/null
+++ b/src/TensorFlowNET.Core/Keras/ArgsDefinition/Preprocessing/ResizingArgs.cs
@@ -0,0 +1,9 @@
+namespace Tensorflow.Keras.ArgsDefinition
+{
+    public class ResizingArgs : LayerArgs
+    {
+        public int Height { get; set; }
+        public int Width { get; set; }
+        public string Interpolation { get; set; } = "bilinear";
+    }
+}
diff --git a/src/TensorFlowNET.Keras/Layers/Preprocessing/Resizing.cs b/src/TensorFlowNET.Keras/Layers/Preprocessing/Resizing.cs
new file mode 100644
index 00000000..eeb813d7
--- /dev/null
+++ b/src/TensorFlowNET.Keras/Layers/Preprocessing/Resizing.cs
@@ -0,0 +1,30 @@
+using System;
+using System.Text;
+using Tensorflow.Keras.ArgsDefinition;
+using Tensorflow.Keras.Engine;
+
+namespace Tensorflow.Keras.Layers
+{
+    /// <summary>
+    /// Resize the batched image input to target height and width. 
+    /// The input should be a 4-D tensor in the format of NHWC.
+    /// </summary>
+    public class Resizing : Layer
+    {
+        ResizingArgs args;
+        public Resizing(ResizingArgs args) : base(args)
+        {
+            this.args = args;
+        }
+
+        protected override Tensors Call(Tensors inputs, Tensor state = null, bool? training = null)
+        {
+            return image_ops_impl.resize_images_v2(inputs, new[] { args.Height, args.Width }, method: args.Interpolation);
+        }
+
+        public override TensorShape ComputeOutputShape(TensorShape input_shape)
+        {
+            return new TensorShape(input_shape.dims[0], args.Height, args.Width, input_shape.dims[3]);
+        }
+    }
+}
diff --git a/src/TensorFlowNET.Keras/Preprocessings/Preprocessing.Resizing.cs b/src/TensorFlowNET.Keras/Preprocessings/Preprocessing.Resizing.cs
new file mode 100644
index 00000000..5e93f583
--- /dev/null
+++ b/src/TensorFlowNET.Keras/Preprocessings/Preprocessing.Resizing.cs
@@ -0,0 +1,26 @@
+using System;
+using System.IO;
+using Tensorflow.Keras.ArgsDefinition;
+using Tensorflow.Keras.Layers;
+using static Tensorflow.KerasApi;
+
+namespace Tensorflow.Keras
+{
+    public partial class Preprocessing
+    {
+        /// <summary>
+        /// Image resizing layer
+        /// </summary>
+        /// <param name="height"></param>
+        /// <param name="width"></param>
+        /// <param name="interpolation"></param>
+        /// <returns></returns>
+        public Resizing Resizing(int height, int width, string interpolation = "bilinear")
+            => new Resizing(new ResizingArgs
+            {
+                Height = height,
+                Width = width,
+                Interpolation = interpolation
+            });
+    }
+}
diff --git a/test/TensorFlowNET.Keras.UnitTest/Layers/LayersTest.cs b/test/TensorFlowNET.Keras.UnitTest/Layers/LayersTest.cs
index 4c9ccb0e..1f4814b9 100644
--- a/test/TensorFlowNET.Keras.UnitTest/Layers/LayersTest.cs
+++ b/test/TensorFlowNET.Keras.UnitTest/Layers/LayersTest.cs
@@ -131,5 +131,13 @@ namespace TensorFlowNET.Keras.UnitTest
             Assert.AreEqual((32, 4), output.shape);
         }
 
+        [TestMethod]
+        public void Resizing()
+        {
+            var inputs = tf.random.uniform((10, 32, 32, 3));
+            var layer = keras.layers.preprocessing.Resizing(16, 16);
+            var output = layer.Apply(inputs);
+            Assert.AreEqual((10, 16, 16, 3), output.shape);
+        }
     }
 }