Merge pull request #14758 from JiabinYang/fix_hs_op_release

fix bug in dist train on hs, test=release/1.2

Author: panyx0718

paddle/fluid/operators/hierarchical_sigmoid_op.cc

@@ -150,13 +150,12 @@ class HierarchicalSigmoidGradOp : public framework::OperatorWithKernel {
                    "Output(W@Grad should not be null.");
     PADDLE_ENFORCE(ctx->HasOutput(framework::GradVarName("X")),
                    "Output(X@Grad should not be null.");
-    if (!ctx->Attrs().Get<bool>("is_sparse")) {
-      if (ctx->HasOutput(framework::GradVarName("Bias"))) {
-        ctx->SetOutputDim(framework::GradVarName("Bias"),
-                          ctx->GetInputDim("Bias"));
-      }
-      ctx->SetOutputDim(framework::GradVarName("W"), ctx->GetInputDim("W"));
+
+    if (ctx->HasOutput(framework::GradVarName("Bias"))) {
+      ctx->SetOutputDim(framework::GradVarName("Bias"),
+                        ctx->GetInputDim("Bias"));
     }
+    ctx->SetOutputDim(framework::GradVarName("W"), ctx->GetInputDim("W"));
     ctx->SetOutputDim(framework::GradVarName("X"), ctx->GetInputDim("X"));
   }