add 2x2s2p1 pooling. test=develop

lite/backends/arm/math/pooling.h

@@ -76,7 +76,7 @@ void pooling1x1s2p0_max(const float* din,
                         int pad_bottom,
                         int pad_right);
 
-void pooling2x2s2_max(const float* din,
+void pooling2x2s2p0_max(const float* din,
                       float* dout,
                       int num,
                       int chout,
@@ -88,7 +88,32 @@ void pooling2x2s2_max(const float* din,
                       int pad_bottom,
                       int pad_right);
 
-void pooling2x2s2_avg(const float* din,
+void pooling2x2s2p0_avg(const float* din,
+                      float* dout,
+                      int num,
+                      int chout,
+                      int hout,
+                      int wout,
+                      int chin,
+                      int hin,
+                      int win,
+                      bool exclusive,
+                      int pad_bottom,
+                      int pad_right);
+
+void pooling2x2s2p1_max(const float* din,
+                      float* dout,
+                      int num,
+                      int chout,
+                      int hout,
+                      int wout,
+                      int chin,
+                      int hin,
+                      int win,
+                      int pad_bottom,
+                      int pad_right);
+
+void pooling2x2s2p1_avg(const float* din,
                       float* dout,
                       int num,
                       int chout,

lite/kernels/arm/pool_compute.cc

@@ -108,7 +108,7 @@ void PoolCompute::Run() {
     } else if (ksize[0] == 2 && strides[0] == 2 && paddings[0] == 0 &&
                kps_equal) {
       if (pooling_type == "max") {
-        lite::arm::math::pooling2x2s2_max(din,
+        lite::arm::math::pooling2x2s2p0_max(din,
                                           dout,
                                           out_dims[0],
                                           out_dims[1],
@@ -121,7 +121,37 @@ void PoolCompute::Run() {
                                           paddings[3]);
         return;
       } else if (pooling_type == "avg") {
-        lite::arm::math::pooling2x2s2_avg(din,
+        lite::arm::math::pooling2x2s2p0_avg(din,
+                                          dout,
+                                          out_dims[0],
+                                          out_dims[1],
+                                          out_dims[2],
+                                          out_dims[3],
+                                          in_dims[1],
+                                          in_dims[2],
+                                          in_dims[3],
+                                          exclusive,
+                                          paddings[1],
+                                          paddings[3]);
+        return;
+      }
+    } else if (ksize[0] == 2 && strides[0] == 2 && paddings[0] == 1 &&
+               kps_equal) {
+      if (pooling_type == "max") {
+        lite::arm::math::pooling2x2s2p1_max(din,
+                                          dout,
+                                          out_dims[0],
+                                          out_dims[1],
+                                          out_dims[2],
+                                          out_dims[3],
+                                          in_dims[1],
+                                          in_dims[2],
+                                          in_dims[3],
+                                          paddings[1],
+                                          paddings[3]);
+        return;
+      } else if (pooling_type == "avg") {
+        lite::arm::math::pooling2x2s2p1_avg(din,
                                           dout,
                                           out_dims[0],
                                           out_dims[1],