follow comments

paddle/operators/math/CMakeLists.txt

@@ -3,14 +3,14 @@ if(WITH_GPU)
     nv_test(math_function_test SRCS math_function_test.cc DEPS math_function tensor)
     nv_library(softmax SRCS softmax.cc softmax.cu DEPS operator)
     nv_library(cross_entropy SRCS cross_entropy.cc cross_entropy.cu DEPS operator)
-    nv_library(pooling SRCS pooling.cc pooling.cu DEPS operator)
+    nv_library(pooling SRCS pooling.cc pooling.cu DEPS device_context)
     nv_library(vol2col SRCS vol2col.cc vol2col.cu DEPS device_context)
 else()
     cc_library(math_function SRCS math_function.cc im2col.cc DEPS cblas device_context operator)
     cc_test(math_function_test SRCS math_function_test.cc DEPS math_function tensor)
     cc_library(softmax SRCS softmax.cc DEPS operator)
     cc_library(cross_entropy SRCS cross_entropy.cc DEPS operator)
-    cc_library(pooling SRCS pooling.cc DEPS operator)
+    cc_library(pooling SRCS pooling.cc DEPS device_context)
     cc_library(vol2col SRCS vol2col.cc DEPS device_context)
 endif()
 

paddle/operators/pool_op.cc

@@ -35,7 +35,7 @@ void PoolOp::InferShape(framework::InferShapeContext *ctx) const {
   std::vector<int> paddings = ctx->Attrs().Get<std::vector<int>>("paddings");
 
   PADDLE_ENFORCE(in_x_dims.size() == 4 || in_x_dims.size() == 5,
-                 "Pooling intput should be 4-D or 5-D");
+                 "Pooling intput should be 4-D or 5-D tensor.");
 
   if (ctx->Attrs().Get<bool>("globalPooling")) {
     ksize.resize(static_cast<size_t>(in_x_dims.size()) - 2);
@@ -70,11 +70,11 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
     : OpProtoAndCheckerMaker(proto, op_checker) {
   AddInput(
       "X",
-      "The input tensor of pooling operator. "
+      "(Tensor) The input tensor of pooling operator. "
       "The format of input tensor is NCHW. Where N is batch size, C is the "
       "number of channels, H and W is the height and width of feature.");
   AddOutput("Out",
-            "The output tensor of pooling operator."
+            "(Tensor) The output tensor of pooling operator."
             "The format of output tensor is also NCHW."
             "Where N is batch size, C is "
             "the number of channels, H and W is the height and "
@@ -87,7 +87,7 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
 
   AddAttr<std::vector<int>>(
       "ksize",
-      "The pooling size(height, width) of pooling operator."
+      "The pooling window size(height, width) of pooling operator."
       "If globalPooling = true, ksize is ignored and need not be "
       "specified.");  // TODO(Chengduo): Add checker. (Currently,
                       // TypedAttrChecker don't support vector type.)
@@ -99,12 +99,12 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
       "If globalPooling = true, ksize is ignored and need not be specified.")
       .SetDefault(false);
   AddAttr<std::vector<int>>("strides",
-                            "Strides(height, width) of pooling operator."
+                            "The strides(height, width) of pooling window."
                             "Default {1,1}.")
       .SetDefault({1, 1});  // TODO(Chengduo): Add checker. (Currently,
                             // TypedAttrChecker don't support vector type.)
   AddAttr<std::vector<int>>("paddings",
-                            "Paddings(height, width) of pooling operator."
+                            "The zero padding(height, width) size on both sides"
                             "Default {0,0}.")
       .SetDefault({0, 0});  // TODO(Chengduo): Add checker. (Currently,
                             // TypedAttrChecker don't support vector type.)
@@ -116,6 +116,17 @@ Input(X) and output(Out) are in NCHW format. Where N is batch size, C is the
 number of channels, H and W is the height and width of feature.
 Parameters(ksize, strides, paddings) are two elements.
 These two elements represent height and width, respectively.
+The input(X) size and output(Out) size may be different.
+
+Example:
+  Input:
+       X shape: (N, C, H_in, W_in)
+  Output:
+       Out shape: (N, C, H_out, W_out)
+       Mask shape: (N, C, H_out, W_out)
+  where
+       H_out = (H_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
+       W_out = (W_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
 )DOC");
 }
 
@@ -124,12 +135,12 @@ Pool3dOpMaker::Pool3dOpMaker(framework::OpProto *proto,
     : OpProtoAndCheckerMaker(proto, op_checker) {
   AddInput(
       "X",
-      "The input tensor of pooling operator. "
+      "(Tensor) The input tensor of pooling operator. "
       "The format of input tensor is NCDHW. Where N is batch size, C is "
       "the number of channels, D, H and W is the depth, height and width of "
       "feature.");
   AddOutput("Out",
-            "The output tensor of pooling operator."
+            "(Tensor) The output tensor of pooling operator."
             "The format of output tensor is also NCDHW."
             "Where N is batch size, C is "
             "the number of channels, D, H and W is the depth, height and "
@@ -142,7 +153,7 @@ Pool3dOpMaker::Pool3dOpMaker(framework::OpProto *proto,
 
   AddAttr<std::vector<int>>(
       "ksize",
-      "The pooling size(depth, height, width) of pooling operator."
+      "The pooling window size(depth, height, width) of pooling operator."
       "If globalPooling = true, ksize is ignored and need not be "
       "specified.");  // TODO(Chengduo): Add checker. (Currently,
                       // TypedAttrChecker don't support vector type.)
@@ -172,6 +183,18 @@ Input(X) and output(Out) are in NCDHW format. Where N is batch
 size, C is the number of channels, D, H and W is the depth, height and
 width of feature. Parameters(ksize, strides, paddings) are three elements.
 These three elements represent depth, height and width, respectively.
+The input(X) size and output(Out) size may be different.
+
+Example:
+  Input:
+       X shape: (N, C, D_in, H_in, W_in)
+  Output:
+       Out shape: (N, C, D_out, H_out, W_out)
+       Mask shape: (N, C, D_out, H_out, W_out)
+  where
+       D_out = (D_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
+       H_out = (H_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
+       W_out = (W_in - ksize[2] + 2 * paddings[2]) / strides[2] + 1;
 )DOC");
 }
 }  // namespace operators

paddle/operators/pool_with_index_op.cc

@@ -43,7 +43,7 @@ class MaxPoolWithIndexOp : public framework::OperatorWithKernel {
     std::vector<int> paddings = ctx->Attrs().Get<std::vector<int>>("paddings");
 
     PADDLE_ENFORCE(in_x_dims.size() == 4 || in_x_dims.size() == 5,
-                   "Pooling intput should be 4-D or 5-D");
+                   "Pooling intput should be 4-D or 5-D tensor.");
 
     if (ctx->Attrs().Get<bool>("globalPooling")) {
       ksize.resize(static_cast<size_t>(in_x_dims.size()) - 2);
@@ -74,8 +74,8 @@ class MaxPoolWithIndexOpGrad : public framework::OperatorWithKernel {
 
  protected:
   void InferShape(framework::InferShapeContext *ctx) const override {
-    PADDLE_ENFORCE(ctx->HasInput("X"), "Input(X) must not be null.");
     PADDLE_ENFORCE(ctx->HasInput("Mask"), "Input(Mask) must not be null.");
+    PADDLE_ENFORCE(ctx->HasInput("X"), "Input(X) must not be null.");
     PADDLE_ENFORCE(ctx->HasOutput(framework::GradVarName("X")),
                    "Input(X@GRAD) should not be null.");
     ctx->SetOutputDim(framework::GradVarName("X"), ctx->GetInputDim("X"));
@@ -89,17 +89,17 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
       : OpProtoAndCheckerMaker(proto, op_checker) {
     AddInput(
         "X",
-        "The input tensor of pooling operator. "
+        "(Tensor) The input tensor of pooling operator. "
         "The format of input tensor is NCHW. Where N is batch size, C is the "
         "number of channels, H and W is the height and width of image.");
     AddOutput("Out",
-              "The output tensor of pooling operator."
+              "(Tensor) The output tensor of pooling operator."
               "The format of output tensor is also NCHW."
               "Where N is batch size, C is "
               "the number of channels, H and W is the height and "
               "width of image.");
     AddOutput("Mask",
-              "The Mask tensor of pooling operator."
+              "(Tensor) The Mask tensor of pooling operator."
               "The format of output tensor is also NCHW."
               "Where N is batch size, C is the number of channels, H and W "
               "is the height and width of image."
@@ -107,7 +107,7 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
 
     AddAttr<std::vector<int>>(
         "ksize",
-        "The pooling size(height, width) of pooling operator."
+        "The pooling window size(height, width) of pooling operator."
         "If globalPooling = true, ksize is ignored and need not be "
         "specified.");  // TODO(Chengduo): Add checker. (Currently,
                         // TypedAttrChecker don't support vector type.)
@@ -119,12 +119,13 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
         "If globalPooling = true, ksize is ignored and need not be specified.")
         .SetDefault(false);
     AddAttr<std::vector<int>>("strides",
-                              "Strides(height, width) of pooling operator."
+                              "The strides(height, width) of pooling window."
                               "Default {1,1}.")
         .SetDefault({1, 1});  // TODO(Chengduo): Add checker. (Currently,
                               // TypedAttrChecker don't support vector type.)
-    AddAttr<std::vector<int>>("paddings",
-                              "Paddings(height, width) of pooling operator."
+    AddAttr<std::vector<int>>(
+        "paddings",
+        "The zero padding(height, width) size on both sides"
         "Default {0,0}.")
         .SetDefault({0, 0});  // TODO(Chengduo): Add checker. (Currently,
                               // TypedAttrChecker don't support vector type.)
@@ -136,6 +137,17 @@ output(Out, Mask) are in NCHW format. Where N is batch size, C is the
 number of channels, H and W is the height and width of feature.
 Parameters(ksize, strides, paddings) are two elements.
 These two elements represent height and width, respectively.
+The input(X) size and output(Out, Mask) size may be different.
+
+Example:
+  Input:
+       X shape: (N, C, H_in, W_in)
+  Output:
+       Out shape: (N, C, H_out, W_out)
+       Mask shape: (N, C, H_out, W_out)
+  where
+       H_out = (H_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
+       W_out = (W_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
 )DOC");
   }
 };
@@ -147,18 +159,18 @@ class MaxPool3dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
       : OpProtoAndCheckerMaker(proto, op_checker) {
     AddInput(
         "X",
-        "The input tensor of pooling operator. "
+        "(Tensor) The input tensor of pooling operator. "
         "The format of input tensor is NCDHW. Where N is batch size, C is "
         "the number of channels, D, H and W is the depth, height and width of "
         "image.");
     AddOutput("Out",
-              "The output tensor of pooling operator."
+              "(Tensor) The output tensor of pooling operator."
               "The format of output tensor is also NCDHW."
               "Where N is batch size, C is "
               "the number of channels, D, H and W is the depth, height and "
               "width of image.");
     AddOutput("Mask",
-              "The Mask tensor of pooling operator."
+              "(Tensor) The Mask tensor of pooling operator."
               "The format of output tensor is also NCDHW."
               "Where N is batch size, C is the number of channels, D, H and W "
               "is the depth, height and width of image."
@@ -166,7 +178,7 @@ class MaxPool3dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
 
     AddAttr<std::vector<int>>(
         "ksize",
-        "The pooling size(depth, height, width) of pooling operator."
+        "The pooling window size(depth, height, width) of pooling operator."
         "If globalPooling = true, ksize is ignored and need not be "
         "specified.");  // TODO(Chengduo): Add checker. (Currently,
                         // TypedAttrChecker don't support vector type.)
@@ -197,6 +209,18 @@ Input(X) and output(Out, Mask) are in NCDHW format. Where N is batch
 size, C is the number of channels, D, H and W is the depth, height and
 width of feature. Parameters(ksize, strides, paddings) are three elements.
 These three elements represent depth, height and width, respectively.
+The input(X) size and output(Out, Mask) size may be different.
+
+Example:
+  Input:
+       X shape: (N, C, D_in, H_in, W_in)
+  Output:
+       Out shape: (N, C, D_out, H_out, W_out)
+       Mask shape: (N, C, D_out, H_out, W_out)
+  where
+       D_out = (D_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
+       H_out = (H_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
+       W_out = (W_in - ksize[2] + 2 * paddings[2]) / strides[2] + 1;
 )DOC");
   }
 };