Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into my-paddle

paddle/operators/sequence_avg_pool_op.cc

@@ -63,7 +63,9 @@ class SequenceAvgPoolGradOp : public framework::OperatorWithKernel {
  protected:
   void InferShape(const framework::InferShapeContext& ctx) const override {
     PADDLE_ENFORCE_NOT_NULL(ctx.InputVar(framework::GradVarName("Out")),
-                            "Gradient of Out should not be null");
+                            "Gradient of Out should not be null.");
+    PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("X"),
+                            "The input X should not be null.");
     auto og_dims =
         ctx.Input<framework::LoDTensor>(framework::GradVarName("Out"))->dims();
     auto x_dims = ctx.Input<framework::LoDTensor>("X")->dims();

paddle/operators/sequence_avg_pool_op.h

@@ -21,6 +21,9 @@ namespace operators {
 
 using Tensor = framework::Tensor;
 using LoDTensor = framework::LoDTensor;
+template <typename T, int MajorType = Eigen::RowMajor,
+          typename IndexType = Eigen::DenseIndex>
+using EigenVector = framework::EigenVector<T, MajorType, IndexType>;
 template <typename T, int MajorType = Eigen::RowMajor,
           typename IndexType = Eigen::DenseIndex>
 using EigenMatrix = framework::EigenMatrix<T, MajorType, IndexType>;
@@ -43,8 +46,8 @@ class SequenceAvgPoolKernel : public framework::OpKernel {
                                  static_cast<int>(lod[0][i + 1]));
       Tensor out_t = out->Slice<T>(i, i + 1);
       int64_t h = static_cast<int64_t>(lod[0][i + 1] - lod[0][i]);
-      auto in_e = EigenMatrix<T>::From(in_t, {h, w});
-      auto out_e = EigenMatrix<T>::From(out_t, {h, w});
+      auto in_e = EigenMatrix<T>::From(in_t, framework::make_ddim({h, w}));
+      auto out_e = EigenVector<T>::Flatten(out_t);
       out_e.device(place) = in_e.mean(Eigen::array<int, 1>({{0}}));
     }
   }
@@ -54,9 +57,9 @@ template <typename Place, typename T>
 class SequenceAvgPoolGradKernel : public framework::OpKernel {
  public:
   void Compute(const framework::ExecutionContext& context) const override {
-    auto* in = context.Output<LoDTensor>("X");
-    auto* in_g = context.Output<LoDTensor>(framework::GradVarName("X"));
+    auto* in = context.Input<LoDTensor>("X");
     auto* out_g = context.Input<LoDTensor>(framework::GradVarName("Out"));
+    auto* in_g = context.Output<LoDTensor>(framework::GradVarName("X"));
 
     auto dims = in->dims();
     auto lod = in->lod();
@@ -71,7 +74,7 @@ class SequenceAvgPoolGradKernel : public framework::OpKernel {
       int64_t h = static_cast<int64_t>(lod[0][i + 1] - lod[0][i]);
       auto in_g_e = EigenMatrix<T>::From(in_g_t, {h, w});
       auto out_g_e = EigenMatrix<T>::From(out_g_t, {1, w});
-      Eigen::DSizes<int, 2> bcast(h, w);
+      Eigen::DSizes<int, 2> bcast(h, 1);
       in_g_e.device(place) = (out_g_e / static_cast<T>(h)).broadcast(bcast);
     }
   }

python/paddle/v2/framework/tests/op_test.py

@@ -47,17 +47,24 @@ def set_input(scope, op, inputs, place):
         if in_name in inputs:
             if in_dup:
                 sub_in = inputs[in_name]
-                for sub_in_name, sub_in_array in sub_in:
+                for sub_in_name, sub_in_val in sub_in:
                     var = scope.find_var(sub_in_name)
                     tensor = var.get_tensor()
+                    sub_in_array = sub_in_val[0] \
+                        if isinstance(sub_in_val, tuple) else sub_in_val
                     tensor.set_dims(sub_in_array.shape)
                     tensor.set(sub_in_array, place)
+                    if isinstance(sub_in_val, tuple):
+                        tensor.set_lod(sub_in_val[1])
             else:
                 var = scope.find_var(in_name)
                 tensor = var.get_tensor()
-                arr = inputs[in_name]
-                tensor.set_dims(arr.shape)
-                tensor.set(arr, place)
+                in_val = inputs[in_name]
+                in_array = in_val[0] if isinstance(in_val, tuple) else in_val
+                tensor.set_dims(in_array.shape)
+                tensor.set(in_array, place)
+                if isinstance(in_val, tuple):
+                    tensor.set_lod(in_val[1])
 
 
 def set_output_grad(scope, op, outputs, place):

python/paddle/v2/framework/tests/test_seq_pool.py

+import unittest
+import numpy as np
+from op_test import OpTest
+
+
+class TestSeqAvgPool1D(OpTest):
+    def setUp(self):
+        self.op_type = 'sequence_avg_pool'
+        # one level, batch size is 4
+        x = np.random.uniform(0.1, 1, [11, 23]).astype('float32')
+        lod = [[0, 4, 5, 8, 11]]
+
+        out = np.zeros((4, 23)).astype('float32')
+        for i in range(4):
+            sub_x = x[lod[0][i]:lod[0][i + 1], :]
+            out[i] = sub_x.mean(axis=0)
+
+        self.inputs = {'X': (x, lod)}
+        self.outputs = {'Out': out}
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad(self):
+        self.check_grad(["X"], "Out")
+
+
+class TestSeqAvgPool2D(OpTest):
+    def setUp(self):
+        self.op_type = 'sequence_avg_pool'
+        # one level, batch size is 4
+        x = np.random.uniform(0.1, 1, [13, 3, 17]).astype('float32')
+        lod = [[0, 4, 5, 8, 13]]
+
+        out = np.zeros((4, 3, 17)).astype('float32')
+        for i in range(4):
+            sub_x = np.reshape(x[lod[0][i]:lod[0][i + 1], :], (-1, 3 * 17))
+            out[i] = np.reshape(sub_x.mean(axis=0), (3, 17))
+
+        self.inputs = {'X': (x, lod)}
+        self.outputs = {'Out': out}
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad(self):
+        self.check_grad(["X"], "Out")
+
+
+if __name__ == '__main__':
+    unittest.main()