Merge pull request #3857 from qingqing01/grad_test_for_multi_inputs

Enhance the unit test framework to explicitly test whether the operator correctly handles gradients for multiple inputs.

doc/howto/dev/new_op_cn.md

@@ -286,28 +286,50 @@ class TestMulOp(unittest.TestCase):
 
 反向Op单测继承自`GradientChecker`，而`GradientChecker`集成自`unittest.TestCase`，所以反向单测函数需要`test_`开头。
 
- ```
- class MulGradOpTest(GradientChecker):
-    def test_mul(self):
-        op = create_op("mul")
-        inputs = {
+```
+class TestMulGradOp(GradientChecker):
+    def setUp(self):
+        self.op = create_op("mul")
+        self.inputs = {
             'X': np.random.random((32, 84)).astype("float32"),
             'Y': np.random.random((84, 100)).astype("float32")
         }
-        self.compare_grad(op, inputs)      
+
+    def test_cpu_gpu_compare(self):
+        self.compare_grad(self.op, self.inputs)
+
+    def test_normal(self):
         # mul op will enlarge the relative error
         self.check_grad(
-            op, inputs, set(["X", "Y"]), "Out", max_relative_error=0.5)
- ```
+            self.op, self.inputs, ["X", "Y"], "Out", max_relative_error=0.5)
+
+    def test_ignore_x(self):
+        self.check_grad(
+            self.op,
+            self.inputs, ["Y"],
+            "Out",
+            max_relative_error=0.5,
+            no_grad_set={"X"})
+
+    def test_ignore_y(self):
+        self.check_grad(
+            self.op,
+            self.inputs, ["X"],
+            "Out",
+            max_relative_error=0.5,
+            no_grad_set={"Y"})
+```
+
+下面解释一些关键的地方:
 
    - 调用`create_op("mul")`创建反向Op对应的前向Op。
-   - 定义输入`inputs`。
    - 调用`compare_grad`函数对比CPU、GPU计算结果。
-   - 调用`check_grad`检查梯度稳定性，这里采用数值法检测梯度正确性。
-      - 第一个参数`op` : 前向op。
-      - 第二个参数`inputs` : 输入词典，词典的Key和`ProtoMaker`定义保持一致。
-      - 第三个参数`set(["X", "Y"])` : 指定对输入变量`X`、`Y`做梯度检测。
+   - `test_normal`中调用`check_grad`检查梯度稳定性，这里采用数值法检测梯度正确性。
+      - 第一个参数`self.op` : 前向Op。
+      - 第二个参数`self.inputs` : 输入词典，词典的Key和`ProtoMaker`定义保持一致。
+      - 第三个参数`["X", "Y"]` : 指定对输入变量`X`、`Y`做梯度检测。
       - 第四个参数`"Out"` : 指定前向网络最终的输出目标变量`Out`
+   - `test_ignore_x`和`test_ignore_y`分支测试只需要计算一个输入梯度的情况。
 
 
 ### 编译和执行 

paddle/operators/mul_op.cc

@@ -75,8 +75,8 @@ class MulOpGrad : public framework::OperatorWithKernel {
     PADDLE_ENFORCE(y_dims[1] == out_dims[1],
                    "Out@GRAD M X N must equal to Y dims 1, N ");
 
-    x_grad->Resize(x_dims);
-    y_grad->Resize(y_dims);
+    if (x_grad) x_grad->Resize(x_dims);
+    if (y_grad) y_grad->Resize(y_dims);
   }
 };
 

paddle/operators/mul_op.h

@@ -31,13 +31,13 @@ template <typename Place, typename T>
 class MulKernel : public framework::OpKernel {
  public:
   void Compute(const framework::ExecutionContext& context) const override {
-    auto* X = context.Input<Tensor>("X");
-    auto* Y = context.Input<Tensor>("Y");
-    auto* Z = context.Output<Tensor>("Out");
-    Z->mutable_data<T>(context.GetPlace());
+    auto* x = context.Input<Tensor>("X");
+    auto* y = context.Input<Tensor>("Y");
+    auto* z = context.Output<Tensor>("Out");
+    z->mutable_data<T>(context.GetPlace());
     auto* device_context =
         const_cast<platform::DeviceContext*>(context.device_context_);
-    math::matmul<Place, T>(*X, false, *Y, false, 1, Z, 0, device_context);
+    math::matmul<Place, T>(*x, false, *y, false, 1, z, 0, device_context);
   }
 };
 
@@ -45,20 +45,24 @@ template <typename Place, typename T>
 class MulGradKernel : public framework::OpKernel {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
-    auto* X = ctx.Input<Tensor>("X");
-    auto* Y = ctx.Input<Tensor>("Y");
-    auto* dOut = ctx.Input<Tensor>(framework::GradVarName("Out"));
+    auto* x = ctx.Input<Tensor>("X");
+    auto* y = ctx.Input<Tensor>("Y");
+    auto* dout = ctx.Input<Tensor>(framework::GradVarName("Out"));
 
-    auto* dX = ctx.Output<Tensor>(framework::GradVarName("X"));
-    auto* dY = ctx.Output<Tensor>(framework::GradVarName("Y"));
-    dX->mutable_data<T>(ctx.GetPlace());
-    dY->mutable_data<T>(ctx.GetPlace());
+    auto* dx = ctx.Output<Tensor>(framework::GradVarName("X"));
+    auto* dy = ctx.Output<Tensor>(framework::GradVarName("Y"));
     auto* device_context =
         const_cast<platform::DeviceContext*>(ctx.device_context_);
-    // dX = dOut * Y'. dX: M x K, dOut : M x N, Y : K x N
-    math::matmul<Place, T>(*dOut, false, *Y, true, 1, dX, 0, device_context);
-    // dY = X' * dOut. dY: K x N, dOut : M x N, X : M x K
-    math::matmul<Place, T>(*X, true, *dOut, false, 1, dY, 0, device_context);
+    if (dx) {
+      dx->mutable_data<T>(ctx.GetPlace());
+      // dx = dout * y'. dx: M x K, dout : M x N, y : K x N
+      math::matmul<Place, T>(*dout, false, *y, true, 1, dx, 0, device_context);
+    }
+    if (dy) {
+      dy->mutable_data<T>(ctx.GetPlace());
+      // dy = x' * dout. dy K x N, dout : M x N, x : M x K
+      math::matmul<Place, T>(*x, true, *dout, false, 1, dy, 0, device_context);
+    }
   }
 };
 

paddle/operators/rowwise_add_op.cc

@@ -64,8 +64,10 @@ class RowwiseAddGradOp : public framework::OperatorWithKernel {
     auto dims0 = ctx.Input<Tensor>("X")->dims();
     auto dims1 = ctx.Input<Tensor>("b")->dims();
     PADDLE_ENFORCE_EQ(1, dims1.size(), "b dims should be 1")
-    ctx.Output<Tensor>(framework::GradVarName("X"))->Resize(dims0);
-    ctx.Output<Tensor>(framework::GradVarName("b"))->Resize(dims1);
+    auto *dx = ctx.Output<Tensor>(framework::GradVarName("X"));
+    auto *db = ctx.Output<Tensor>(framework::GradVarName("b"));
+    if (dx) dx->Resize(dims0);
+    if (db) db->Resize(dims1);
   }
 };
 

paddle/operators/rowwise_add_op.h

@@ -51,20 +51,24 @@ template <typename Place, typename T>
 class RowwiseAddGradKernel : public framework::OpKernel {
  public:
   void Compute(const framework::ExecutionContext& context) const override {
-    auto* dOut = context.Input<Tensor>(framework::GradVarName("Out"));
-    auto* dX = context.Output<Tensor>(framework::GradVarName("X"));
+    auto* dout = context.Input<Tensor>(framework::GradVarName("Out"));
+    auto* dx = context.Output<Tensor>(framework::GradVarName("X"));
     auto* db = context.Output<Tensor>(framework::GradVarName("b"));
-    dX->mutable_data<T>(context.GetPlace());
-    db->mutable_data<T>(context.GetPlace());
 
-    auto OutGrad = EigenMatrix<T>::From(*dOut);
+    auto out_grad = EigenMatrix<T>::From(*dout);
     auto place = context.GetEigenDevice<Place>();
-    EigenMatrix<T>::From(*dX).device(place) = OutGrad;
+    if (dx) {
+      dx->mutable_data<T>(context.GetPlace());
+      EigenMatrix<T>::From(*dx).device(place) = out_grad;
+    }
 
+    if (db) {
+      db->mutable_data<T>(context.GetPlace());
       // https://eigen.tuxfamily.org/dox/unsupported/TensorBase_8h_source.html
       // colwise add
       Eigen::array<int, 1> dims{{0}}; /* dimension to reduce */
-    EigenVector<T>::Flatten(*db).device(place) = OutGrad.sum(dims);
+      EigenVector<T>::Flatten(*db).device(place) = out_grad.sum(dims);
+    }
   }
 };
 }  // namespace operators

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

@@ -286,6 +286,9 @@ class GradientChecker(unittest.TestCase):
         for no_grad in no_grad_set:
             if no_grad not in in_names:
                 raise ValueError("no_grad should be in in_names")
+            if no_grad in inputs_to_check:
+                raise ValueError("no_grad should not be in inputs_to_check")
+
         backward_op = core.Operator.backward(forward_op, no_grad_set)
 
         places = [core.CPUPlace()]
@@ -301,7 +304,6 @@ class GradientChecker(unittest.TestCase):
 
         check_names = [grad_var_name(name) for name in inputs_to_check]
         for place in places:
-            # get analytical gradients according to different device
             analytic_grads = self.__get_gradient(forward_op, backward_op,
                                                  input_vars, check_names, place)
             self.__assert_is_close(numeric_grads, analytic_grads, check_names,

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

@@ -16,16 +16,37 @@ class TestMulOp(unittest.TestCase):
         self.outputs = {'Out': np.dot(self.inputs['X'], self.inputs['Y'])}
 
 
-class MulGradOpTest(GradientChecker):
-    def test_mul(self):
-        op = create_op("mul")
-        inputs = {
+class TestMulGradOp(GradientChecker):
+    def setUp(self):
+        self.op = create_op("mul")
+        self.inputs = {
             'X': np.random.random((32, 84)).astype("float32"),
             'Y': np.random.random((84, 100)).astype("float32")
         }
+
+    def test_cpu_gpu_compare(self):
+        self.compare_grad(self.op, self.inputs)
+
+    def test_normal(self):
         # mul op will enlarge the relative error
         self.check_grad(
-            op, inputs, set(["X", "Y"]), "Out", max_relative_error=0.5)
+            self.op, self.inputs, ["X", "Y"], "Out", max_relative_error=0.5)
+
+    def test_ignore_x(self):
+        self.check_grad(
+            self.op,
+            self.inputs, ["Y"],
+            "Out",
+            max_relative_error=0.5,
+            no_grad_set={"X"})
+
+    def test_ignore_y(self):
+        self.check_grad(
+            self.op,
+            self.inputs, ["X"],
+            "Out",
+            max_relative_error=0.5,
+            no_grad_set={"Y"})
 
 
 # TODO(dzh,qijun) : mulgrad test case need transpose feature of blas library

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

@@ -16,14 +16,22 @@ class TestRowwiseAddOp(unittest.TestCase):
         self.outputs = {'Out': np.add(self.inputs['X'], self.inputs['b'])}
 
 
-class RowwiseAddGradOpTest(GradientChecker):
-    def test_rowwise_add(self):
-        op = create_op("rowwise_add")
-        inputs = {
+class TestRowwiseAddGradOp(GradientChecker):
+    def setUp(self):
+        self.op = create_op("rowwise_add")
+        self.inputs = {
             "X": np.random.uniform(0.1, 1, [5, 10]).astype("float32"),
             "b": np.random.uniform(0.1, 1, [10]).astype("float32")
         }
-        self.check_grad(op, inputs, set(["X", "b"]), "Out")
+
+    def test_normal(self):
+        self.check_grad(self.op, self.inputs, ["X", "b"], "Out")
+
+    def test_ignore_b(self):
+        self.check_grad(self.op, self.inputs, ["X"], "Out", no_grad_set={"b"})
+
+    def test_ignore_x(self):
+        self.check_grad(self.op, self.inputs, ["b"], "Out", no_grad_set={"X"})
 
 
 if __name__ == '__main__':