Fix/sequence op (#5264)

* "replace enum with string"

* "fix layers"

paddle/operators/sequence_pool_op.cc

@@ -39,15 +39,14 @@ class SequencePoolOpMaker : public framework::OpProtoAndCheckerMaker {
     AddOutput("Out",
               "(Tensor), output of SequencePoolOp, which does not contain LoD "
               "infomation.");
-    AddAttr<int>(
-        "strategy",
-        "(int, default AVERAGE) the pooling strategy of SequencePoolOp.")
-        .SetDefault(AVERAGE)
-        .InEnum({AVERAGE, SUM, SQRT, MAX, LAST, FIRST});
+    AddAttr<std::string>(
+        "pooltype",
+        "(int, default AVERAGE) the pooling pooltype of SequencePoolOp.")
+        .SetDefault("AVERAGE");
     AddComment(R"DOC(
     SequencePoolOp pools features of all time-steps of each instance.
 
-    It supports six pooling strategy:
+    It supports six pooling pooltype:
     - AVERAGE: Out[i] = average_{for each instance in i-th sequence}{X[i]}
     - SUM:     Out[i] = sum_{for each instance in i-th sequence}{X[i]}
     - SQRT:    Out[i] = sum_{for each instance in i-th sequence}{X[i]} 
@@ -63,7 +62,7 @@ class SequencePoolOpMaker : public framework::OpProtoAndCheckerMaker {
     and the value of X = [[1, 3], [2, 4, 6], [5, 1]].
 
     Thus, Out is a [3,1,1] Tensor without LoD infomation.
-    And for different strategy, the value of Out is as follows:
+    And for different pooltype, the value of Out is as follows:
 
     - AVERAGE: [2, 4, 3], where 2=(1+3)/2, 4=(2+4+6)/3, 3=(5+1)/2
     - SUM: [4, 12, 6], where 4=1+3, 12=2+4+6, 6=5+1

paddle/operators/sequence_pool_op.h

@@ -29,22 +29,13 @@ template <typename T, int MajorType = Eigen::RowMajor,
           typename IndexType = Eigen::DenseIndex>
 using EigenMatrix = framework::EigenMatrix<T, MajorType, IndexType>;
 
-enum SeqPoolType {
-  AVERAGE = 0,
-  SUM = 1,
-  SQRT = 2,  // square_root_n
-  MAX = 3,
-  LAST = 4,
-  FIRST = 5
-};
-
 template <typename Place, typename T>
 class SequencePoolKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& context) const override {
     auto* in = context.Input<LoDTensor>("X");
     auto* out = context.Output<LoDTensor>("Out");
-    int strategy = context.Attr<int>("strategy");
+    std::string pooltype = context.Attr<std::string>("pooltype");
 
     auto dims = in->dims();
     auto lod = in->lod();
@@ -71,28 +62,21 @@ class SequencePoolKernel : public framework::OpKernel<T> {
       auto in_e = EigenMatrix<T>::From(in_t, framework::make_ddim({h, w}));
       auto out_e = EigenVector<T>::Flatten(out_t);
 
-      switch (strategy) {
-        case AVERAGE:
+      if (pooltype == "AVERAGE") {
         out_e.device(place) = in_e.mean(Eigen::array<int, 1>({{0}}));
-          break;
-        case SUM:
+      } else if (pooltype == "SUM") {
         out_e.device(place) = in_e.sum(Eigen::array<int, 1>({{0}}));
-          break;
-        case SQRT:
+      } else if (pooltype == "SQRT") {
         out_e.device(place) = in_e.sum(Eigen::array<int, 1>({{0}})) /
                               std::sqrt(static_cast<T>(h));
-          break;
-        case MAX:
+      } else if (pooltype == "MAX") {
         out_e.device(place) = in_e.maximum(Eigen::array<int, 1>({{0}}));
-          break;
-        case LAST:
+      } else if (pooltype == "LAST") {
         out_e.device(place) = in_e.chip(h - 1, 0);
-          break;
-        case FIRST:
+      } else if (pooltype == "FIRST") {
         out_e.device(place) = in_e.chip(0, 0);
-          break;
-        default:
-          PADDLE_THROW("unsupported pooling strategy");
+      } else {
+        PADDLE_THROW("unsupported pooling pooltype");
       }
     }
   }
@@ -105,15 +89,15 @@ class SequencePoolGradKernel : public framework::OpKernel<T> {
     auto* in = context.Input<LoDTensor>("X");
     auto* in_g = context.Output<LoDTensor>(framework::GradVarName("X"));
     auto* out_g = context.Input<LoDTensor>(framework::GradVarName("Out"));
-    int strategy = context.Attr<int>("strategy");
+    std::string pooltype = context.Attr<std::string>("pooltype");
 
     auto dims = in->dims();
     auto lod = in->lod()[0];
     int64_t w = in->numel() / dims[0];
 
     in_g->mutable_data<T>(context.GetPlace());
-    if (strategy == LAST || strategy == FIRST) {
-      // set X@Grad be zero at first when strategy is LAST/FIRST
+    if (pooltype == "LAST" || pooltype == "FIRST") {
+      // set X@Grad be zero at first when pooltype is LAST/FIRST
       math::SetConstant<Place, T> functor;
       functor(context.device_context(), in_g, 0);
     }
@@ -127,18 +111,14 @@ class SequencePoolGradKernel : public framework::OpKernel<T> {
       auto out_g_e = EigenMatrix<T>::From(out_g_t, {1, w});
       Eigen::DSizes<int, 2> bcast(h, 1);
 
-      switch (strategy) {
-        case AVERAGE:
+      if (pooltype == "AVERAGE") {
         in_g_e.device(place) = (out_g_e / static_cast<T>(h)).broadcast(bcast);
-          break;
-        case SUM:
+      } else if (pooltype == "SUM") {
         in_g_e.device(place) = (out_g_e).broadcast(bcast);
-          break;
-        case SQRT:
+      } else if (pooltype == "SQRT") {
         in_g_e.device(place) =
             (out_g_e / std::sqrt(static_cast<T>(h))).broadcast(bcast);
-          break;
-        case MAX: {
+      } else if (pooltype == "MAX") {
         auto in_t =
             in->Slice(static_cast<int>(lod[i]), static_cast<int>(lod[i + 1]));
         Eigen::Map<const Eigen::Matrix<T, Eigen::Dynamic, Eigen::Dynamic>>
@@ -152,16 +132,12 @@ class SequencePoolGradKernel : public framework::OpKernel<T> {
           in_g_e.slice(in_offsets, extents).device(place) =
               out_g_e.slice(out_offsets, extents);
         }
-          break;
-        }
-        case LAST:
+      } else if (pooltype == "LAST") {
         in_g_e.chip(h - 1, 0).device(place) = out_g_e;
-          break;
-        case FIRST:
+      } else if (pooltype == "FIRST") {
         in_g_e.chip(0, 0).device(place) = out_g_e;
-          break;
-        default:
-          PADDLE_THROW("unsupported pooling strategy");
+      } else {
+        PADDLE_THROW("unsupported pooling pooltype");
       }
     }
   }

python/paddle/v2/framework/layers.py

@@ -351,32 +351,21 @@ def conv2d(input,
     return helper.append_activation(pre_act)
 
 
-def sequence_pool(input, pool_type, program=None, init_program=None):
-    # FIXME(dzh) : want to unify the argument of python layer
-    # function. So we ignore some unecessary attributes
-
-    ENUM_POOL_TYPE = dict({
-        "AVERAGE": 0,
-        "SUM": 1,
-        "SQRT": 2,
-        "MAX": 3,
-        "LAST": 4,
-        "FIRST": 5
-    })
+def sequence_pool(input, pool_type, **kwargs):
+    ENUM_POOL_TYPE = set(["MAX", "AVG", "SQRT", "LAST", "FIRST"])
     if pool_type.upper() not in ENUM_POOL_TYPE:
         raise ValueError("Unknown pool_type: '%s'. It can only be %s.",
-                         str(pool_type), " ".join(ENUM_POOL_TYPE.keys()))
+                         str(pool_type), " ".join(ENUM_POOL_TYPE))
 
-    helper = LayerHelper('sequence_pool', **locals())
+    helper = LayerHelper('sequence_pool', **kwargs)
     dtype = helper.input_dtype()
     pool_out = helper.create_tmp_variable(dtype)
 
-    # FIXME(dzh): strategy
     helper.append_op(
         type="sequence_pool",
         inputs={"X": [input]},
         outputs={"Out": [pool_out]},
-        attrs={"strategy": ENUM_POOL_TYPE[pool_type.upper()]})
+        attrs={"pooltype": pool_type.upper()})
 
     return pool_out
 

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

@@ -3,15 +3,6 @@ import numpy as np
 from op_test import OpTest
 
 
-class SeqPoolType(OpTest):
-    AVERAGE = 0
-    SUM = 1
-    SQRT = 2
-    MAX = 3
-    LAST = 4
-    FIRST = 5
-
-
 class TestSeqAvgPool(OpTest):
     def set_data(self):
         self.op_type = 'sequence_pool'
@@ -25,7 +16,7 @@ class TestSeqAvgPool(OpTest):
         return x, lod, out
 
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.AVERAGE}
+        self.attrs = {'pooltype': "AVERAGE"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             out[i] = sub_x.mean(axis=0)
@@ -54,7 +45,7 @@ class TestSeqAvgPool2D(TestSeqAvgPool):
         return x, lod, out
 
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.AVERAGE}
+        self.attrs = {'pooltype': "AVERAGE"}
         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))
@@ -62,7 +53,7 @@ class TestSeqAvgPool2D(TestSeqAvgPool):
 
 class TestSeqSumPool(TestSeqAvgPool):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.SUM}
+        self.attrs = {'pooltype': "SUM"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             out[i] = sub_x.sum(axis=0)
@@ -70,7 +61,7 @@ class TestSeqSumPool(TestSeqAvgPool):
 
 class TestSeqSumPool2D(TestSeqAvgPool2D):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.SUM}
+        self.attrs = {'pooltype': "SUM"}
         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.sum(axis=0), (3, 17))
@@ -78,7 +69,7 @@ class TestSeqSumPool2D(TestSeqAvgPool2D):
 
 class TestSeqSqrtPool(TestSeqAvgPool):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.SQRT}
+        self.attrs = {'pooltype': "SQRT"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             len = lod[0][i + 1] - lod[0][i]
@@ -87,7 +78,7 @@ class TestSeqSqrtPool(TestSeqAvgPool):
 
 class TestSeqSqrtPool2D(TestSeqAvgPool2D):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.SQRT}
+        self.attrs = {'pooltype': "SQRT"}
         for i in range(4):
             sub_x = np.reshape(x[lod[0][i]:lod[0][i + 1], :], (-1, 3 * 17))
             len = lod[0][i + 1] - lod[0][i]
@@ -99,7 +90,7 @@ class TestSeqSqrtPool2D(TestSeqAvgPool2D):
 
 class TestSeqMaxPool(TestSeqAvgPool):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.MAX}
+        self.attrs = {'pooltype': "MAX"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             out[i] = np.amax(sub_x, axis=0)
@@ -111,7 +102,7 @@ class TestSeqMaxPool(TestSeqAvgPool):
 
 class TestSeqMaxPool2D(TestSeqAvgPool2D):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.MAX}
+        self.attrs = {'pooltype': "MAX"}
         for i in range(4):
             sub_x = np.reshape(x[lod[0][i]:lod[0][i + 1], :], (-1, 3 * 17))
             out[i] = np.reshape(np.amax(sub_x, axis=0), (3, 17))
@@ -123,7 +114,7 @@ class TestSeqMaxPool2D(TestSeqAvgPool2D):
 
 class TestSeqLastPool(TestSeqAvgPool):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.LAST}
+        self.attrs = {'pooltype': "LAST"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             out[i] = sub_x[-1, :]
@@ -131,7 +122,7 @@ class TestSeqLastPool(TestSeqAvgPool):
 
 class TestSeqLastPool2D(TestSeqAvgPool2D):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.LAST}
+        self.attrs = {'pooltype': "LAST"}
         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[-1, :], (3, 17))
@@ -139,7 +130,7 @@ class TestSeqLastPool2D(TestSeqAvgPool2D):
 
 class TestSeqFirstPool(TestSeqAvgPool):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.FIRST}
+        self.attrs = {'pooltype': "FIRST"}
         for i in range(4):
             sub_x = x[lod[0][i]:lod[0][i + 1], :]
             out[i] = sub_x[0, :]
@@ -147,7 +138,7 @@ class TestSeqFirstPool(TestSeqAvgPool):
 
 class TestSeqFirstPool2D(TestSeqAvgPool2D):
     def compute(self, x, lod, out):
-        self.attrs = {'strategy': SeqPoolType.FIRST}
+        self.attrs = {'pooltype': "FIRST"}
         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[0, :], (3, 17))