make cross_entropy_op supporting tensors

Author: JiayiFeng

paddle/fluid/framework/tensor.cc

@@ -112,5 +112,6 @@ Tensor& Tensor::Resize(const DDim& dims) {
 const DDim& Tensor::dims() const { return dims_; }
 
 int64_t Tensor::numel() const { return product(dims_); }
+
 }  // namespace framework
 }  // namespace paddle

paddle/fluid/operators/cross_entropy_op.h

@@ -33,8 +33,14 @@ class CrossEntropyOpKernel : public framework::OpKernel<T> {
     auto* y = ctx.Output<Tensor>("Y");
     y->mutable_data<T>(ctx.GetPlace());
 
+    int rank = x->dims().size();
+    Tensor x_2d = rank > 2 ? framework::ReshapeToMatrix(*x, rank - 1) : *x;
+    Tensor labels_2d =
+        rank > 2 ? framework::ReshapeToMatrix(*labels, rank - 1) : *labels;
+    Tensor y_2d = rank > 2 ? framework::ReshapeToMatrix(*y, rank - 1) : *y;
+
     math::CrossEntropyFunctor<DeviceContext, T>()(
-        ctx.template device_context<DeviceContext>(), y, x, labels,
+        ctx.template device_context<DeviceContext>(), &y_2d, &x_2d, &labels_2d,
         ctx.Attr<bool>("soft_label"));
   }
 };
@@ -98,9 +104,12 @@ class CrossEntropyGradientOpKernel : public framework::OpKernel<T> {
     auto* dy = ctx.Input<Tensor>(framework::GradVarName("Y"));
     auto* label = ctx.Input<Tensor>("Label");
     auto* dx = ctx.Output<Tensor>(framework::GradVarName("X"));
-    auto* dx_data = dx->mutable_data<T>(ctx.GetPlace());
+    T* dx_data = dx->mutable_data<T>(ctx.GetPlace());
 
-    int64_t class_num = x->dims()[1];
+    // Following computation only depends on the last dimension size. So it's
+    // unnecessary to convert tensors to 2-D views.
+    int rank = x->dims().size();
+    int64_t class_num = x->dims()[rank - 1];
     if (ctx.Attr<bool>("soft_label")) {
       XeSoftlabelGradFunctor<T> functor(dx_data, dy->data<T>(), x->data<T>(),
                                         label->data<T>(),

python/paddle/fluid/tests/unittests/test_cross_entropy_op.py

@@ -105,5 +105,107 @@ def test_check_grad(self):
             ["X"], "Y", max_relative_error=0.05, numeric_grad_delta=0.001)
 
 
+class TestCrossEntropyOp4(OpTest):
+    """Test high rank tensor cross-entropy with discrete one-hot labels.
+    """
+
+    def setUp(self):
+        self.op_type = "cross_entropy"
+        shape = [10, 2, 4]
+        ins_num = np.prod(np.array(shape))
+        class_num = 10
+
+        X_2d = randomize_probability(ins_num, class_num, dtype='float64')
+
+        label_2d = np.random.randint(0, class_num, (ins_num, 1), dtype="int64")
+        cross_entropy_2d = np.asmatrix(
+            [[-np.log(X_2d[i][label_2d[i][0]])] for i in range(X_2d.shape[0])],
+            dtype="float64")
+
+        X = X_2d.reshape(shape + [class_num])
+        label = label_2d.reshape(shape + [1])
+        cross_entropy = np.array(cross_entropy_2d).reshape(shape + [1])
+
+        self.inputs = {"X": X, "Label": label}
+        self.outputs = {"Y": cross_entropy}
+        self.attrs = {"soft_label": False}
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad(self):
+        self.check_grad(["X"], "Y", numeric_grad_delta=0.001)
+
+
+class TestCrossEntropyOp5(OpTest):
+    """Test high rank tensor cross-entropy with vectorized soft labels.
+    """
+
+    def setUp(self):
+        self.op_type = "cross_entropy"
+        shape = [4, 3]
+        ins_num = np.prod(np.array(shape))
+        class_num = 37
+
+        X_2d = randomize_probability(ins_num, class_num)
+        label_2d = np.random.uniform(0.1, 1.0,
+                                     [ins_num, class_num]).astype("float32")
+        label_2d /= label_2d.sum(axis=1, keepdims=True)
+        cross_entropy_2d = (-label_2d * np.log(X_2d)).sum(
+            axis=1, keepdims=True).astype("float32")
+
+        X = X_2d.reshape(shape + [class_num])
+        label = label_2d.reshape(shape + [class_num])
+        cross_entropy = np.array(cross_entropy_2d).reshape(shape + [1])
+
+        self.inputs = {"X": X, "Label": label}
+        self.outputs = {"Y": cross_entropy}
+        self.attrs = {"soft_label": True}
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad(self):
+        self.check_grad(
+            ["X"], "Y", max_relative_error=0.05, numeric_grad_delta=0.001)
+
+
+class TestCrossEntropyOp6(OpTest):
+    """Test high rank tensor cross-entropy with vectorized one-hot representation of labels.
+    """
+
+    def setUp(self):
+        self.op_type = "cross_entropy"
+        shape = [4, 3, 2]
+        ins_num = np.prod(np.array(shape))
+        class_num = 17
+
+        X_2d = randomize_probability(ins_num, class_num)
+        label_index_2d = np.random.randint(
+            0, class_num, (ins_num), dtype="int32")
+        label_2d = np.zeros(X_2d.shape)
+        label_2d[np.arange(ins_num), label_index_2d] = 1
+
+        cross_entropy_2d = np.asmatrix(
+            [[-np.log(X_2d[i][label_index_2d[i]])]
+             for i in range(X_2d.shape[0])],
+            dtype="float32")
+
+        X = X_2d.reshape(shape + [class_num])
+        label = label_2d.reshape(shape + [class_num])
+        cross_entropy = np.array(cross_entropy_2d).reshape(shape + [1])
+
+        self.inputs = {"X": X, "Label": label.astype(np.float32)}
+        self.outputs = {"Y": cross_entropy}
+        self.attrs = {"soft_label": True}
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad(self):
+        self.check_grad(
+            ["X"], "Y", max_relative_error=0.05, numeric_grad_delta=0.001)
+
+
 if __name__ == "__main__":
     unittest.main()