Implement max pooling layer

include/layers/max_pooling.cuh

@@ -0,0 +1,42 @@
+#ifndef CUDANET_MAX_POOLING_H
+#define CUDANET_MAX_POOLING_H
+
+#include <cuda_runtime.h>
+
+#include "layer.cuh"
+#include "activation.cuh"
+
+namespace CUDANet::Layers {
+
+class MaxPooling2D : public SequentialLayer {
+  public:
+    MaxPooling2D(
+        int            inputSize,
+        int            nChannels,
+        int            poolingSize,
+        int            stride,
+        Padding            padding,
+        ActivationType activationType
+    );
+    ~MaxPooling2D();
+
+    float* forward(const float* d_input);
+
+  private:
+    int inputSize;
+    int nChannels;
+    int poolingSize;
+    int stride;
+    int paddingSize;
+
+    int outputSize;
+    int gridSize;
+
+    float* d_output;
+
+    Activation activation;
+};
+
+}  // namespace CUDANet::Layers
+
+#endif  // CUDANET_MAX_POOLING_H