Fix CPPLint errors in multiclass_nms, nccl, nce, reduce and save_load_combine (#10032)

* Fix CPPLint errors in multiclass_nms, nccl, nce, reduce and save_load_combine

* Fix

paddle/fluid/operators/multiclass_nms_op.cc

@@ -173,8 +173,8 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
 
   void MultiClassNMS(const framework::ExecutionContext& ctx,
                      const Tensor& scores, const Tensor& bboxes,
-                     std::map<int, std::vector<int>>& indices,
-                     int& num_nmsed_out) const {
+                     std::map<int, std::vector<int>>* indices,
+                     int* num_nmsed_out) const {
     int64_t background_label = ctx.Attr<int>("background_label");
     int64_t nms_top_k = ctx.Attr<int>("nms_top_k");
     int64_t keep_top_k = ctx.Attr<int>("keep_top_k");
@@ -189,15 +189,15 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
       if (c == background_label) continue;
       Tensor score = scores.Slice(c, c + 1);
       NMSFast(bboxes, score, score_threshold, nms_threshold, nms_eta, nms_top_k,
-              &(indices[c]));
-      num_det += indices[c].size();
+              &((*indices)[c]));
+      num_det += (*indices)[c].size();
     }
 
-    num_nmsed_out = num_det;
+    *num_nmsed_out = num_det;
     const T* scores_data = scores.data<T>();
     if (keep_top_k > -1 && num_det > keep_top_k) {
       std::vector<std::pair<float, std::pair<int, int>>> score_index_pairs;
-      for (const auto& it : indices) {
+      for (const auto& it : *indices) {
         int label = it.first;
         const T* sdata = scores_data + label * predict_dim;
         const std::vector<int>& label_indices = it.second;
@@ -220,13 +220,13 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
         int idx = score_index_pairs[j].second.second;
         new_indices[label].push_back(idx);
       }
-      new_indices.swap(indices);
-      num_nmsed_out = keep_top_k;
+      new_indices.swap(*indices);
+      *num_nmsed_out = keep_top_k;
     }
   }
 
   void MultiClassOutput(const Tensor& scores, const Tensor& bboxes,
-                        std::map<int, std::vector<int>>& selected_indices,
+                        const std::map<int, std::vector<int>>& selected_indices,
                         Tensor* outs) const {
     int predict_dim = scores.dims()[1];
     auto* scores_data = scores.data<T>();
@@ -273,7 +273,7 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
 
       std::map<int, std::vector<int>> indices;
       int num_nmsed_out = 0;
-      MultiClassNMS(ctx, ins_score, ins_boxes, indices, num_nmsed_out);
+      MultiClassNMS(ctx, ins_score, ins_boxes, &indices, &num_nmsed_out);
       all_indices.push_back(indices);
       batch_starts.push_back(batch_starts.back() + num_nmsed_out);
     }

paddle/fluid/operators/nccl_op.cu.cc

@@ -135,8 +135,9 @@ class NCCLBcastKernel : public framework::OpKernel<T> {
       auto* x = ctx.Input<LoDTensor>("X");
       VLOG(3) << "gpu : " << gpu_id << " invoke Bcast. send " << x->numel();
       PADDLE_ENFORCE(platform::dynload::ncclBcast(
-          (void*)x->data<T>(), x->numel(), NCCLTypeWrapper<T>::type, root,
-          comm->comms().at(idx), ctx.cuda_device_context().stream()));
+          reinterpret_cast<void*>(const_cast<T*>(x->data<T>())), x->numel(),
+          NCCLTypeWrapper<T>::type, root, comm->comms().at(idx),
+          ctx.cuda_device_context().stream()));
       VLOG(3) << "gpu : " << gpu_id << " finished Bcast.";
     } else {
       auto* out = ctx.Output<LoDTensor>("Out");

paddle/fluid/operators/nce_op.h

@@ -16,6 +16,7 @@ limitations under the License. */
 
 #include <math.h>
 #include <random>
+#include <vector>
 #include "paddle/fluid/framework/eigen.h"
 #include "paddle/fluid/framework/op_registry.h"
 #include "unsupported/Eigen/CXX11/Tensor"
@@ -108,7 +109,7 @@ class NCEKernel : public framework::OpKernel<T> {
     auto weight_mat = EigenMatrix<T>::From(*(context.Input<Tensor>("Weight")));
     for (int64_t i = 0; i < sample_labels->numel(); ++i) {
       Eigen::Tensor<T, 0, Eigen::RowMajor, Eigen::DenseIndex> result =
-          (input_mat.chip((int)(i / sample_labels->dims()[1]), 0) *
+          (input_mat.chip(static_cast<int>(i / sample_labels->dims()[1]), 0) *
            weight_mat.chip(sample_labels_data[i], 0))
               .sum();
       sample_out_data[i] += result(0);
@@ -190,7 +191,7 @@ class NCEGradKernel : public framework::OpKernel<T> {
       auto x_matrix = EigenMatrix<T>::From(*(context.Input<Tensor>("Input")));
       for (int64_t i = 0; i < sample_labels->numel(); ++i) {
         d_w_matrix.chip(sample_labels_data[i], 0) +=
-            x_matrix.chip((int)(i / sample_labels->dims()[1]), 0) *
+            x_matrix.chip(static_cast<int>(i / sample_labels->dims()[1]), 0) *
             sample_grad_data[i];
       }
     }
@@ -202,7 +203,7 @@ class NCEGradKernel : public framework::OpKernel<T> {
       auto d_x_matrix = EigenMatrix<T>::From(*d_x);
       auto w_matrix = EigenMatrix<T>::From(*(context.Input<Tensor>("Weight")));
       for (int64_t i = 0; i < sample_labels->numel(); ++i) {
-        d_x_matrix.chip((int)(i / sample_labels->dims()[1]), 0) +=
+        d_x_matrix.chip(static_cast<int>(i / sample_labels->dims()[1]), 0) +=
             w_matrix.chip(sample_labels_data[i], 0) * sample_grad_data[i];
       }
     }

paddle/fluid/operators/reduce_op.h

@@ -35,77 +35,77 @@ using EigenVector = framework::EigenVector<T, MajorType, IndexType>;
 
 struct SumFunctor {
   template <typename DeviceContext, typename X, typename Y, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, const Dim& dim) {
-    y.device(place) = x.sum(dim);
+  void operator()(const DeviceContext& place, X* x, Y* y, const Dim& dim) {
+    y->device(place) = x->sum(dim);
   }
 };
 
 struct SumGradFunctor {
   template <typename DeviceContext, typename X, typename Y, typename DX,
             typename DY, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, DX& dx, DY& dy,
+  void operator()(const DeviceContext& place, X* x, Y* y, DX* dx, DY* dy,
                   const Dim& dim, int size) {
-    dx.device(place) = dy.broadcast(dim);
+    dx->device(place) = dy->broadcast(dim);
   }
 };
 
 struct MeanFunctor {
   template <typename DeviceContext, typename X, typename Y, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, const Dim& dim) {
-    y.device(place) = x.mean(dim);
+  void operator()(const DeviceContext& place, X* x, Y* y, const Dim& dim) {
+    y->device(place) = x->mean(dim);
   }
 };
 
 struct MeanGradFunctor {
   template <typename DeviceContext, typename X, typename Y, typename DX,
             typename DY, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, DX& dx, DY& dy,
+  void operator()(const DeviceContext& place, X* x, Y* y, DX* dx, DY* dy,
                   const Dim& dim, int size) {
-    dx.device(place) = dy.broadcast(dim) / dx.constant(size);
+    dx->device(place) = dy->broadcast(dim) / dx->constant(size);
   }
 };
 
 struct MaxFunctor {
   template <typename DeviceContext, typename X, typename Y, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, const Dim& dim) {
-    y.device(place) = x.maximum(dim);
+  void operator()(const DeviceContext& place, X* x, Y* y, const Dim& dim) {
+    y->device(place) = x->maximum(dim);
   }
 };
 
 struct MinFunctor {
   template <typename DeviceContext, typename X, typename Y, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, const Dim& dim) {
-    y.device(place) = x.minimum(dim);
+  void operator()(const DeviceContext& place, X* x, Y* y, const Dim& dim) {
+    y->device(place) = x->minimum(dim);
   }
 };
 
 struct MaxOrMinGradFunctor {
   template <typename DeviceContext, typename X, typename Y, typename DX,
             typename DY, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, DX& dx, DY& dy,
+  void operator()(const DeviceContext& place, X* x, Y* y, DX* dx, DY* dy,
                   const Dim& dim, int size) {
-    auto equals = x == y.broadcast(dim);
-    auto ones = dx.constant(1);
-    auto zeros = dx.constant(0);
+    auto equals = (*x) == y->broadcast(dim);
+    auto ones = dx->constant(1);
+    auto zeros = dx->constant(0);
     // If there are multiple minimum or maximum elements, the subgradient of
     // each is the set [0, 1], and we pass gradient to all of them here.
-    dx.device(place) = dy.broadcast(dim) * equals.select(ones, zeros);
+    dx->device(place) = dy->broadcast(dim) * equals.select(ones, zeros);
   }
 };
 
 struct ProdFunctor {
   template <typename DeviceContext, typename X, typename Y, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, const Dim& dim) {
-    y.device(place) = x.prod(dim);
+  void operator()(const DeviceContext& place, X* x, Y* y, const Dim& dim) {
+    y->device(place) = x->prod(dim);
   }
 };
 
 struct ProdGradFunctor {
   template <typename DeviceContext, typename X, typename Y, typename DX,
             typename DY, typename Dim>
-  void operator()(const DeviceContext& place, X& x, Y& y, DX& dx, DY& dy,
+  void operator()(const DeviceContext& place, X* x, Y* y, DX* dx, DY* dy,
                   const Dim& dim, int size) {
-    dx.device(place) = dy.broadcast(dim) * y.broadcast(dim) * x.inverse();
+    dx->device(place) = dy->broadcast(dim) * y->broadcast(dim) * x->inverse();
   }
 };
 
@@ -125,7 +125,7 @@ class ReduceKernel : public framework::OpKernel<T> {
           *context.template device_context<DeviceContext>().eigen_device();
       auto reduce_dim = Eigen::array<int, 1>({{0}});
       Functor functor;
-      functor(place, x, out, reduce_dim);
+      functor(place, &x, &out, reduce_dim);
     } else {
       int rank = context.Input<Tensor>("X")->dims().size();
       switch (rank) {
@@ -178,10 +178,10 @@ class ReduceKernel : public framework::OpKernel<T> {
 
     if (D == 1) {
       auto out = EigenScalar<T>::From(*output);
-      functor(place, x, out, reduce_dim);
+      functor(place, &x, &out, reduce_dim);
     } else {
       auto out = EigenTensor<T, (D - 1)>::From(*output, dims);
-      functor(place, x, out, reduce_dim);
+      functor(place, &x, &out, reduce_dim);
     }
   }
 };
@@ -206,7 +206,7 @@ class ReduceGradKernel : public framework::OpKernel<T> {
       auto broadcast_dim =
           Eigen::array<int, 1>({{static_cast<int>(input0->numel())}});
       Functor functor;
-      functor(place, x, x_reduce, x_grad, x_reduce_grad, broadcast_dim,
+      functor(place, &x, &x_reduce, &x_grad, &x_reduce_grad, broadcast_dim,
               broadcast_dim[0]);
     } else {
       int rank = context.Input<Tensor>("X")->dims().size();
@@ -258,7 +258,7 @@ class ReduceGradKernel : public framework::OpKernel<T> {
     auto& place =
         *context.template device_context<DeviceContext>().eigen_device();
     Functor functor;
-    functor(place, x, x_reduce, x_grad, x_reduce_grad, broadcast_dim,
+    functor(place, &x, &x_reduce, &x_grad, &x_reduce_grad, broadcast_dim,
             broadcast_dim[dim]);
   }
 };

paddle/fluid/operators/save_load_combine_op_test.cc

@@ -23,17 +23,17 @@ USE_NO_KERNEL_OP(load_combine);
 
 int* CreateForSaveCombineOp(int x, int y, const std::vector<int>& lod_info,
                             std::string var_name,
-                            paddle::platform::CPUPlace& place,
-                            paddle::framework::Scope& scope,
-                            paddle::framework::LoD& expect_lod) {
-  auto var = scope.Var(var_name);
+                            const paddle::platform::CPUPlace& place,
+                            paddle::framework::Scope* scope,
+                            paddle::framework::LoD* expect_lod) {
+  auto var = scope->Var(var_name);
   auto tensor = var->GetMutable<paddle::framework::LoDTensor>();
   tensor->Resize({x, y});
-  expect_lod.resize(1);
+  expect_lod->resize(1);
   for (size_t i = 0; i < lod_info.size(); i++) {
-    expect_lod[0].push_back(lod_info[i]);
+    (*expect_lod)[0].push_back(lod_info[i]);
   }
-  tensor->set_lod(expect_lod);
+  tensor->set_lod(*expect_lod);
   int* expect = tensor->mutable_data<int>(place);
   for (int64_t i = 0; i < tensor->numel(); ++i) {
     expect[i] = static_cast<int>(i);
@@ -42,17 +42,17 @@ int* CreateForSaveCombineOp(int x, int y, const std::vector<int>& lod_info,
 }
 
 paddle::framework::LoDTensor* GeneratePlaceholderBeforeLoad(
-    const std::string out_var_name, paddle::framework::Scope& scope) {
-  auto load_var = scope.Var(out_var_name);
+    const std::string out_var_name, paddle::framework::Scope* scope) {
+  auto load_var = scope->Var(out_var_name);
   auto target = load_var->GetMutable<paddle::framework::LoDTensor>();
   return target;
 }
 
 int* GetValuesAfterLoadCombineOp(paddle::framework::LoDTensor* target,
-                                 paddle::framework::Scope& scope,
-                                 paddle::framework::LoD& actual_lod) {
+                                 const paddle::framework::Scope& scope,
+                                 paddle::framework::LoD* actual_lod) {
   int* actual = target->data<int>();
-  actual_lod = target->lod();
+  *actual_lod = target->lod();
   return actual;
 }
 
@@ -78,26 +78,26 @@ TEST(SaveLoadCombineOp, CPU) {
   std::vector<int> lod1 = {0, 1, 2, 3, 10};
   int numel1 = 100;
   paddle::framework::LoD expect_lod1;
-  int* expect1 = CreateForSaveCombineOp(10, 10, lod1, "test_var1", place, scope,
-                                        expect_lod1);
+  int* expect1 = CreateForSaveCombineOp(10, 10, lod1, "test_var1", place,
+                                        &scope, &expect_lod1);
 
   std::vector<int> lod2 = {0, 2, 5, 10};
   int numel2 = 200;
   paddle::framework::LoD expect_lod2;
-  int* expect2 = CreateForSaveCombineOp(10, 20, lod2, "test_var2", place, scope,
-                                        expect_lod2);
+  int* expect2 = CreateForSaveCombineOp(10, 20, lod2, "test_var2", place,
+                                        &scope, &expect_lod2);
 
   std::vector<int> lod3 = {0, 2, 3, 20};
   int numel3 = 4000;
   paddle::framework::LoD expect_lod3;
   int* expect3 = CreateForSaveCombineOp(20, 200, lod3, "test_var3", place,
-                                        scope, expect_lod3);
+                                        &scope, &expect_lod3);
 
   std::vector<int> lod4 = {0, 1, 20};
   int numel4 = 1000;
   paddle::framework::LoD expect_lod4;
-  int* expect4 = CreateForSaveCombineOp(20, 50, lod4, "test_var4", place, scope,
-                                        expect_lod4);
+  int* expect4 = CreateForSaveCombineOp(20, 50, lod4, "test_var4", place,
+                                        &scope, &expect_lod4);
 
   // Set attributes
   std::string filename = "check_tensor.ls";
@@ -111,10 +111,10 @@ TEST(SaveLoadCombineOp, CPU) {
   save_combine_op->Run(scope, place);
 
   // Set up output vars
-  auto target1 = GeneratePlaceholderBeforeLoad("out_var1", scope);
-  auto target2 = GeneratePlaceholderBeforeLoad("out_var2", scope);
-  auto target3 = GeneratePlaceholderBeforeLoad("out_var3", scope);
-  auto target4 = GeneratePlaceholderBeforeLoad("out_var4", scope);
+  auto target1 = GeneratePlaceholderBeforeLoad("out_var1", &scope);
+  auto target2 = GeneratePlaceholderBeforeLoad("out_var2", &scope);
+  auto target3 = GeneratePlaceholderBeforeLoad("out_var3", &scope);
+  auto target4 = GeneratePlaceholderBeforeLoad("out_var4", &scope);
 
   // Run the load_combine_op
   auto load_combine_op = paddle::framework::OpRegistry::CreateOp(
@@ -123,10 +123,10 @@ TEST(SaveLoadCombineOp, CPU) {
   load_combine_op->Run(scope, place);
 
   paddle::framework::LoD actual_lod1, actual_lod2, actual_lod3, actual_lod4;
-  int* actual1 = GetValuesAfterLoadCombineOp(target1, scope, actual_lod1);
-  int* actual2 = GetValuesAfterLoadCombineOp(target2, scope, actual_lod2);
-  int* actual3 = GetValuesAfterLoadCombineOp(target3, scope, actual_lod3);
-  int* actual4 = GetValuesAfterLoadCombineOp(target4, scope, actual_lod4);
+  int* actual1 = GetValuesAfterLoadCombineOp(target1, scope, &actual_lod1);
+  int* actual2 = GetValuesAfterLoadCombineOp(target2, scope, &actual_lod2);
+  int* actual3 = GetValuesAfterLoadCombineOp(target3, scope, &actual_lod3);
+  int* actual4 = GetValuesAfterLoadCombineOp(target4, scope, &actual_lod4);
 
   CheckValues(expect1, actual1, expect_lod1, actual_lod1, numel1);
   CheckValues(expect2, actual2, expect_lod2, actual_lod2, numel2);