Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pr/11489

AUTHORS.md

@@ -22,6 +22,7 @@
 | jczaja | Jacek Czaja |
 | JiayiFeng | Jia-Yi Feng |
 | kbinias | Krzysztof Binias |
+| kexinzhao | Ke-Xin Zhao |
 | kuke | Yi-Bing Liu |
 | lcy-seso | Ying Cao |
 | lipeng-unisound | Peng Li |

benchmark/fluid/models/machine_translation.py

@@ -173,21 +173,6 @@ def seq_to_seq_net(embedding_dim, encoder_size, decoder_size, source_dict_dim,
         return avg_cost, feeding_list
 
 
-def to_lodtensor(data, place):
-    seq_lens = [len(seq) for seq in data]
-    cur_len = 0
-    lod = [cur_len]
-    for l in seq_lens:
-        cur_len += l
-        lod.append(cur_len)
-    flattened_data = np.concatenate(data, axis=0).astype("int64")
-    flattened_data = flattened_data.reshape([len(flattened_data), 1])
-    lod_t = core.LoDTensor()
-    lod_t.set(flattened_data, place)
-    lod_t.set_lod([lod])
-    return lod_t, lod[-1]
-
-
 def lodtensor_to_ndarray(lod_tensor):
     dims = lod_tensor.get_dims()
     ndarray = np.zeros(shape=dims).astype('float32')

benchmark/fluid/models/stacked_dynamic_lstm.py

@@ -125,18 +125,3 @@ def get_model(args):
         batch_size=args.batch_size)
 
     return loss, inference_program, adam, train_reader, test_reader, batch_acc
-
-
-def to_lodtensor(data, place):
-    seq_lens = [len(seq) for seq in data]
-    cur_len = 0
-    lod = [cur_len]
-    for l in seq_lens:
-        cur_len += l
-        lod.append(cur_len)
-    flattened_data = numpy.concatenate(data, axis=0).astype("int64")
-    flattened_data = flattened_data.reshape([len(flattened_data), 1])
-    res = fluid.LoDTensor()
-    res.set(flattened_data, place)
-    res.set_lod([lod])
-    return res

cmake/inference_lib.cmake

@@ -39,7 +39,7 @@ function(copy TARGET)
         message(FATAL_ERROR "${TARGET} source numbers are not equal to destination numbers")
     endif()
     math(EXPR len "${copy_lib_SRCS_len} - 1")
-    
+
     add_custom_target(${TARGET} DEPENDS ${copy_lib_DEPS})
     foreach(index RANGE ${len})
         list(GET copy_lib_SRCS ${index} src)
@@ -155,6 +155,15 @@ copy(inference_lib DEPS paddle_fluid_shared paddle_fluid
   DSTS ${dst_dir}/${module} ${dst_dir}/${module}
 )
 
+if(WITH_CONTRIB)
+   set(contrib_dst_dir "${FLUID_INSTALL_DIR}/contrib/inference")
+   copy(contrib_inference_lib DEPS paddle_inference_api
+        SRCS ${PADDLE_SOURCE_DIR}/paddle/contrib/inference/paddle_inference_api.h
+        ${PADDLE_BINARY_DIR}/paddle/contrib/inference/libpaddle_inference_api.*
+        DSTS ${contrib_dst_dir} ${contrib_dst_dir}
+   )
+endif()
+
 set(module "platform")
 copy(platform_lib DEPS profiler_py_proto
   SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/dynload/*.h ${src_dir}/${module}/details/*.h

doc/fluid/api/gen_doc.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-python gen_doc.py layers --submodules control_flow device io nn ops tensor detection learning_rate_scheduler > layers.rst
+python gen_doc.py layers --submodules control_flow device io nn ops tensor detection learning_rate_scheduler metric > layers.rst
 
 for module in data_feeder clip metrics executor initializer io nets optimizer param_attr profiler regularizer
 do

doc/fluid/api/initializer.rst

@@ -33,6 +33,13 @@ Xavier
     :members:
     :noindex:
 
+Bilinear
+--------
+
+..  autoclass:: paddle.fluid.initializer.Bilinear
+    :members:
+    :noindex:
+
 force_init_on_cpu
 -----------------
 
@@ -73,3 +80,10 @@ XavierInitializer
     :members:
     :noindex:
 
+BilinearInitializer
+-------------------
+
+..  autoclass:: paddle.fluid.initializer.BilinearInitializer
+    :members:
+    :noindex:
+

doc/fluid/api/io.rst

@@ -59,3 +59,39 @@ get_inference_program
 ..  autofunction:: paddle.fluid.io.get_inference_program
     :noindex:
 
+save_checkpoint
+---------------
+
+..  autofunction:: paddle.fluid.io.save_checkpoint
+    :noindex:
+
+load_checkpoint
+---------------
+
+..  autofunction:: paddle.fluid.io.load_checkpoint
+    :noindex:
+
+clean_checkpoint
+----------------
+
+..  autofunction:: paddle.fluid.io.clean_checkpoint
+    :noindex:
+
+load_persist_vars_without_grad
+------------------------------
+
+..  autofunction:: paddle.fluid.io.load_persist_vars_without_grad
+    :noindex:
+
+save_persist_vars_without_grad
+------------------------------
+
+..  autofunction:: paddle.fluid.io.save_persist_vars_without_grad
+    :noindex:
+
+get_latest_checkpoint_serial
+----------------------------
+
+..  autofunction:: paddle.fluid.io.get_latest_checkpoint_serial
+    :noindex:
+

doc/fluid/api/optimizer.rst

@@ -89,6 +89,13 @@ DecayedAdagradOptimizer
     :members:
     :noindex:
 
+RMSPropOptimizer
+----------------
+
+..  autoclass:: paddle.fluid.optimizer.RMSPropOptimizer
+    :members:
+    :noindex:
+
 Adadelta
 --------
 

doc/fluid/api/profiler.rst

@@ -23,3 +23,15 @@ profiler
 ..  autofunction:: paddle.fluid.profiler.profiler
     :noindex:
 
+start_profiler
+--------------
+
+..  autofunction:: paddle.fluid.profiler.start_profiler
+    :noindex:
+
+stop_profiler
+-------------
+
+..  autofunction:: paddle.fluid.profiler.stop_profiler
+    :noindex:
+

doc/v2/dev/contribute_to_paddle_cn.md

@@ -104,7 +104,7 @@ no changes added to commit (use "git add" and/or "git commit -a")
 ➜  docker run -it -v $(pwd):/paddle paddle:latest-dev bash -c "cd /paddle/build && ctest"
 ```
 
-关于构建和测试的更多信息，请参见[这篇文档](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+关于构建和测试的更多信息，请参见[使用Docker安装运行](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/v2/build_and_install/docker_install_cn.rst)。
 
 ## 提交（commit）
 

paddle/fluid/framework/executor.cc

@@ -406,6 +406,9 @@ void Executor::EnableMKLDNN(const ProgramDesc& program) {
       }
     }
   }
+#else
+  LOG(WARNING)
+      << "'MKLDNN' is not supported, Please re-compile with WITH_MKLDNN option";
 #endif
 }
 

paddle/fluid/framework/lod_tensor.cc

@@ -410,5 +410,38 @@ void LoDTensor::MergeLoDTensor(
   }
 }
 
+LoD ConvertToLengthBasedLoD(const LoD &offset_lod) {
+  LoD length_lod;
+  length_lod.reserve(offset_lod.size());
+  for (size_t lvl = 0; lvl < offset_lod.size(); ++lvl) {
+    std::vector<size_t> level;
+    if (offset_lod[lvl].size() > 0) {
+      level.reserve(offset_lod[lvl].size() - 1);
+    }
+    for (size_t idx = 0; idx < offset_lod[lvl].size() - 1; ++idx) {
+      level.push_back(offset_lod[lvl][idx + 1] - offset_lod[lvl][idx]);
+    }
+    length_lod.push_back(level);
+  }
+  return length_lod;
+}
+
+LoD ConvertToOffsetBasedLoD(const LoD &length_lod) {
+  LoD offset_lod;
+  offset_lod.reserve(length_lod.size());
+  for (size_t lvl = 0; lvl < length_lod.size(); ++lvl) {
+    std::vector<size_t> level;
+    level.reserve(length_lod[lvl].size() + 1);
+    size_t tmp = 0;
+    level.push_back(tmp);
+    for (size_t idx = 0; idx < length_lod[lvl].size(); ++idx) {
+      tmp += length_lod[lvl][idx];
+      level.push_back(tmp);
+    }
+    offset_lod.push_back(level);
+  }
+  return offset_lod;
+}
+
 }  // namespace framework
 }  // namespace paddle

paddle/fluid/framework/lod_tensor.h

@@ -226,5 +226,19 @@ extern void WriteToRecordIO(recordio::Writer* writer,
 extern std::vector<LoDTensor> ReadFromRecordIO(
     recordio::Scanner* scanner, const platform::DeviceContext& dev_ctx);
 
+/*
+ * Convert between length-based LoD and offset-based LoD.
+ * The implementation of LoDTensor class use offset-based LoD.
+ * However, we want to expose the more user-friendly length-based
+ * LoD to the Python side instead.
+ *
+ * Example:
+ * If offset_lod = [[0, 2, 3],[0, 3, 5, 9]]
+ * then length_lod = [[2, 1], [3, 2, 4]]
+ */
+LoD ConvertToLengthBasedLoD(const LoD& offset_lod);
+
+LoD ConvertToOffsetBasedLoD(const LoD& length_lod);
+
 }  // namespace framework
 }  // namespace paddle

paddle/fluid/framework/lod_tensor_test.cc

@@ -228,6 +228,38 @@ TEST(LoD, CheckAbsLoD) {
   ASSERT_FALSE(CheckAbsLoD(abs_lod0));
 }
 
+TEST(LoD, ConvertToLengthBasedLoD) {
+  LoD offset_lod;
+  offset_lod.push_back(std::vector<size_t>({0, 2}));
+  offset_lod.push_back(std::vector<size_t>({0, 1, 3}));
+  offset_lod.push_back(std::vector<size_t>({0, 2, 4, 5}));
+
+  LoD length_lod = ConvertToLengthBasedLoD(offset_lod);
+
+  LoD expected;
+  expected.push_back(std::vector<size_t>({2}));
+  expected.push_back(std::vector<size_t>({1, 2}));
+  expected.push_back(std::vector<size_t>({2, 2, 1}));
+
+  EXPECT_EQ(length_lod, expected);
+}
+
+TEST(LoD, ConvertToOffsetBasedLoD) {
+  LoD length_lod;
+  length_lod.push_back(std::vector<size_t>({2}));
+  length_lod.push_back(std::vector<size_t>({1, 2}));
+  length_lod.push_back(std::vector<size_t>({2, 2, 1}));
+
+  LoD offset_lod = ConvertToOffsetBasedLoD(length_lod);
+
+  LoD expected;
+  expected.push_back(std::vector<size_t>({0, 2}));
+  expected.push_back(std::vector<size_t>({0, 1, 3}));
+  expected.push_back(std::vector<size_t>({0, 2, 4, 5}));
+
+  EXPECT_EQ(offset_lod, expected);
+}
+
 template <typename T>
 static void TestRecordIO() {
   LoDTensor tensor;

paddle/fluid/framework/scope.cc

@@ -43,48 +43,29 @@ Scope& Scope::NewScope() const {
 }
 
 Variable* Scope::Var(const std::string& name) {
-  // acquire the lock when new var under this scope
   std::unique_lock<std::mutex> lock(mutex_);
-  auto* v = FindVarLocally(name);
-  if (v != nullptr) return v;
-
-  v = new Variable();
-  vars_[name].reset(v);
-  VLOG(3) << "Create variable " << name;
-  v->name_ = &(vars_.find(name)->first);
-  return v;
+  return VarInternal(name);
 }
 
 Variable* Scope::Var(std::string* name) {
-  auto var_name = string::Sprintf("%p.%d", this, vars_.size());
+  std::unique_lock<std::mutex> lock(mutex_);
+  auto new_name = string::Sprintf("%p.%d", this, vars_.size());
   if (name != nullptr) {
-    *name = var_name;
+    *name = new_name;
   }
-  return Var(var_name);
+  return VarInternal(new_name);
 }
 
 Variable* Scope::FindVar(const std::string& name) const {
-  // acquire the lock when find var
   std::unique_lock<std::mutex> lock(mutex_);
   return FindVarInternal(name);
 }
 
-Variable* Scope::FindVarInternal(const std::string& name) const {
-  auto var = FindVarLocally(name);
-  if (var != nullptr) {
-    return var;
-  }
-  return (parent_ == nullptr) ? nullptr : parent_->FindVarInternal(name);
-}
-
 const Scope* Scope::FindScope(const Variable* var) const {
-  for (auto& kv : vars_) {
-    if (kv.second.get() == var) {
-      return this;
-    }
-  }
-  return (parent_ == nullptr) ? nullptr : parent_->FindScope(var);
+  std::unique_lock<std::mutex> lock(mutex_);
+  return FindScopeInternal(var);
 }
+
 void Scope::DropKids() {
   std::unique_lock<std::mutex> lock(mutex_);
   for (Scope* s : kids_) delete s;
@@ -92,6 +73,7 @@ void Scope::DropKids() {
 }
 
 std::vector<std::string> Scope::LocalVarNames() const {
+  std::unique_lock<std::mutex> lock(mutex_);
   std::vector<std::string> known_vars;
   known_vars.reserve(this->vars_.size());
   for (auto& p : vars_) {
@@ -127,6 +109,39 @@ void Scope::EraseVars(const std::vector<std::string>& var_names) {
 
 void Scope::Rename(const std::string& origin_name,
                    const std::string& new_name) const {
+  std::unique_lock<std::mutex> lock(mutex_);
+  RenameInternal(origin_name, new_name);
+}
+
+std::string Scope::Rename(const std::string& origin_name) const {
+  std::unique_lock<std::mutex> lock(mutex_);
+  auto new_name = string::Sprintf("%p.%d", this, vars_.size());
+  RenameInternal(origin_name, new_name);
+  return new_name;
+}
+
+Variable* Scope::VarInternal(const std::string& name) {
+  auto* v = FindVarLocally(name);
+  if (v != nullptr) return v;
+
+  v = new Variable();
+  vars_[name].reset(v);
+  VLOG(3) << "Create variable " << name;
+  v->name_ = &(vars_.find(name)->first);
+  return v;
+}
+
+const Scope* Scope::FindScopeInternal(const Variable* var) const {
+  for (auto& kv : vars_) {
+    if (kv.second.get() == var) {
+      return this;
+    }
+  }
+  return (parent_ == nullptr) ? nullptr : parent_->FindScope(var);
+}
+
+void Scope::RenameInternal(const std::string& origin_name,
+                           const std::string& new_name) const {
   auto origin_it = vars_.find(origin_name);
   PADDLE_ENFORCE(origin_it != vars_.end(),
                  "Cannot find original variable with name %s", origin_name);
@@ -137,10 +152,12 @@ void Scope::Rename(const std::string& origin_name,
   vars_.erase(origin_it);
 }
 
-std::string Scope::Rename(const std::string& origin_name) const {
-  auto var_name = string::Sprintf("%p.%d", this, vars_.size());
-  Rename(origin_name, var_name);
-  return var_name;
+Variable* Scope::FindVarInternal(const std::string& name) const {
+  auto var = FindVarLocally(name);
+  if (var != nullptr) {
+    return var;
+  }
+  return (parent_ == nullptr) ? nullptr : parent_->FindVar(name);
 }
 
 Variable* Scope::FindVarLocally(const std::string& name) const {

paddle/fluid/framework/scope.h

@@ -88,12 +88,20 @@ class Scope {
   // Call Scope::NewScope for a sub-scope.
   explicit Scope(Scope const* parent) : parent_(parent) {}
 
+  // Called by Var.
+  Variable* VarInternal(const std::string& name);
+
+  // Called by FindScope.
+  const Scope* FindScopeInternal(const Variable* var) const;
+
+  // Called by Rename.
+  void RenameInternal(const std::string& origin_name,
+                      const std::string& new_name) const;
+
   // Called by FindVar recursively.
-  // Caller doesn't own the returned Variable.
   Variable* FindVarInternal(const std::string& name) const;
 
   // Called by FindVarInternal and Var.
-  // Caller doesn't own the returned Variable.
   Variable* FindVarLocally(const std::string& name) const;
 
   // Scope in `kids_` are owned by this class.

paddle/fluid/inference/tensorrt/convert/op_converter.h

@@ -64,7 +64,8 @@ class OpConverter {
     (*it)(op, scope, test_mode);
   }
 
-  // convert fluid block to tensorrt network
+  // Convert a fluid block to tensorrt network, NOTE it just convert operators,
+  // the INetwork's inputs and outputs should specified in some other modules.
   void ConvertBlock(const framework::proto::BlockDesc& block,
                     const std::unordered_set<std::string>& parameters,
                     const framework::Scope& scope, TensorRTEngine* engine) {

paddle/fluid/inference/tensorrt/engine.h

@@ -51,11 +51,12 @@ class TensorRTEngine : public EngineBase {
     nvinfer1::Weights w_;
   };
 
-  TensorRTEngine(int max_batch, int max_workspace, cudaStream_t* stream,
+  TensorRTEngine(int max_batch, int max_workspace,
+                 cudaStream_t* stream = nullptr,
                  nvinfer1::ILogger& logger = NaiveLogger::Global())
       : max_batch_(max_batch),
         max_workspace_(max_workspace),
-        stream_(stream),
+        stream_(stream ? stream : &default_stream_),
         logger_(logger) {}
 
   virtual ~TensorRTEngine();
@@ -121,6 +122,8 @@ class TensorRTEngine : public EngineBase {
   // the max memory size the engine uses
   int max_workspace_;
   cudaStream_t* stream_;
+  // If stream_ is not set from outside, hold its own stream.
+  cudaStream_t default_stream_;
   nvinfer1::ILogger& logger_;
 
   std::vector<Buffer> buffers_;
@@ -165,20 +168,31 @@ class TensorRTEngine : public EngineBase {
  */
 class TRT_EngineManager {
  public:
-  TensorRTEngine* Create(int max_batch, int max_workspace,
-                         cudaStream_t* stream) {
-    engines_.emplace_back(new TensorRTEngine(max_batch, max_workspace, stream));
-    return engines_.back().get();
+  bool HasEngine(const std::string& name) const {
+    return engines_.count(name) != 0;
+  }
+
+  // Get an engine called `name`.
+  TensorRTEngine* Get(const std::string& name) const {
+    return engines_.at(name).get();
+  }
+
+  // Create or get an engine called `name`
+  TensorRTEngine* Create(int max_batch, int max_workspace, cudaStream_t* stream,
+                         const std::string& name) {
+    auto* p = new TensorRTEngine(max_batch, max_workspace, stream);
+    engines_[name].reset(p);
+    return p;
   }
 
   void DeleteALl() {
-    for (auto& ptr : engines_) {
-      ptr.reset(nullptr);
+    for (auto& item : engines_) {
+      item.second.reset(nullptr);
     }
   }
 
  private:
-  std::vector<std::unique_ptr<TensorRTEngine>> engines_;
+  std::unordered_map<std::string, std::unique_ptr<TensorRTEngine>> engines_;
 };
 
 }  // namespace tensorrt

paddle/fluid/inference/tests/book/test_inference_nlp.cc

@@ -29,6 +29,7 @@ DEFINE_string(data_file, "", "File of input index data.");
 DEFINE_int32(repeat, 100, "Running the inference program repeat times");
 DEFINE_bool(prepare_vars, true, "Prepare variables before executor");
 DEFINE_int32(num_threads, 1, "Number of threads should be used");
+DECLARE_bool(use_mkldnn);
 
 inline double GetCurrentMs() {
   struct timeval time;
@@ -103,9 +104,9 @@ void ThreadRunInfer(
     const int tid, paddle::framework::Scope* scope,
     const std::vector<std::vector<const paddle::framework::LoDTensor*>>& jobs) {
   // maybe framework:ProgramDesc is not thread-safe
+  paddle::platform::CPUPlace place;
+  paddle::framework::Executor executor(place);
   auto& sub_scope = scope->NewScope();
-  auto place = paddle::platform::CPUPlace();
-  auto executor = paddle::framework::Executor(place);
   auto inference_program =
       paddle::inference::Load(&executor, scope, FLAGS_model_path);
 
@@ -182,8 +183,8 @@ TEST(inference, nlp) {
     stop_ms = GetCurrentMs();
   } else {
     // 1. Define place, executor, scope
-    auto place = paddle::platform::CPUPlace();
-    auto executor = paddle::framework::Executor(place);
+    paddle::platform::CPUPlace place;
+    paddle::framework::Executor executor(place);
 
     // 2. Initialize the inference_program and load parameters
     std::unique_ptr<paddle::framework::ProgramDesc> inference_program;

paddle/fluid/operators/activation_op.cc

@@ -19,18 +19,18 @@ limitations under the License. */
 namespace paddle {
 namespace operators {
 
-#define REGISTER_ACTIVATION_OP_MAKER(OP_NAME, OP_COMMENT)               \
-  class OP_NAME##OpMaker                                                \
-      : public ::paddle::framework::OpProtoAndCheckerMaker {            \
-   public:                                                              \
-    void Make() override {                                              \
-      AddInput("X", "Input of " #OP_NAME " operator");                  \
-      AddOutput("Out", "Output of " #OP_NAME " operator").Reuse("X");   \
-      AddAttr<bool>("use_mkldnn",                                       \
-                    "(bool, default false) Only used in mkldnn kernel") \
-          .SetDefault(false);                                           \
-      AddComment(OP_COMMENT);                                           \
-    }                                                                   \
+#define REGISTER_ACTIVATION_OP_MAKER(OP_NAME, OP_COMMENT)             \
+  class OP_NAME##OpMaker                                              \
+      : public ::paddle::framework::OpProtoAndCheckerMaker {          \
+   public:                                                            \
+    void Make() override {                                            \
+      AddInput("X", "Input of " #OP_NAME " operator");                \
+      AddOutput("Out", "Output of " #OP_NAME " operator").Reuse("X"); \
+      AddAttr<bool>("use_mkldnn",                                     \
+                    "(default false) Only used in mkldnn kernel")     \
+          .SetDefault(false);                                         \
+      AddComment(OP_COMMENT);                                         \
+    }                                                                 \
   }
 
 #define REGISTER_ACTIVATION_OP_GRAD_MAKER(OP_NAME, KERNEL_TYPE)              \
@@ -112,7 +112,7 @@ $$out = \frac{1}{1 + e^{-x}}$$
 __attribute__((unused)) constexpr char LogSigmoidDoc[] = R"DOC(
 Logsigmoid Activation Operator
 
-$$out = \log \frac{1}{1 + e^{-x}}$$
+$$out = \\log \\frac{1}{1 + e^{-x}}$$
 
 )DOC";
 
@@ -196,7 +196,7 @@ $out = [x]$
 __attribute__((unused)) constexpr char ReciprocalDoc[] = R"DOC(
 Reciprocal Activation Operator.
 
-$$out = \frac{1}{x}$$
+$$out = \\frac{1}{x}$$
 
 )DOC";
 
@@ -252,15 +252,14 @@ class SoftShrinkOpMaker : public framework::OpProtoAndCheckerMaker {
     AddOutput("Out", "Output of Softshrink operator");
     AddAttr<float>("lambda", "non-negative offset").SetDefault(0.5f);
     AddComment(R"DOC(
-Softshrink Activation Operator.
+:strong:`Softshrink Activation Operator`
 
-$$
-out = \begin{cases} 
-    x - \lambda, \text{if } x > \lambda \\
-    x + \lambda, \text{if } x < -\lambda \\
-    0,  \text{otherwise}
-    \end{cases}
-$$
+..  math::
+    out = \begin{cases} 
+         x - \lambda, \text{if } x > \lambda \\
+         x + \lambda, \text{if } x < -\lambda \\
+         0,  \text{otherwise}
+         \end{cases}
 
 )DOC");
   }
@@ -271,18 +270,18 @@ class HardShrinkOpMaker : public framework::OpProtoAndCheckerMaker {
   void Make() override {
     AddInput("X", "Input of HardShrink operator");
     AddOutput("Out", "Output of HardShrink operator");
-    AddAttr<float>("threshold", "The value of threshold for HardShrink")
+    AddAttr<float>("threshold",
+                   "The value of threshold for HardShrink. [default: 0.5]")
         .SetDefault(0.5f);
     AddComment(R"DOC(
-HardShrink Activation Operator.
+:strong:`HardShrink activation operator`
 
-$$
-out = \begin{cases} 
-    x, \text{if } x > \lambda \\
-    x, \text{if } x < -\lambda \\
-    0,  \text{otherwise}
-    \end{cases}
-$$
+..  math::
+    out = \begin{cases}
+            x, \text{if } x > \lambda \\
+            x, \text{if } x < -\lambda \\
+            0,  \text{otherwise}
+          \end{cases}
 
 )DOC");
   }
@@ -394,18 +393,18 @@ class ThresholdedReluOpMaker : public framework::OpProtoAndCheckerMaker {
   void Make() override {
     AddInput("X", "Input of ThresholdedRelu operator");
     AddOutput("Out", "Output of ThresholdedRelu operator");
-    AddAttr<float>("threshold", "The threshold location of activation")
+    AddAttr<float>("threshold",
+                   "The threshold location of activation. [default 1.0].")
         .SetDefault(1.0f);
     AddComment(R"DOC(
-ThresholdedRelu Activation Operator.
+:strong:`ThresholdedRelu activation operator`
 
-$$
-out = \begin{cases} 
-    x, \text{if } x > threshold \\
-    0,  \text{otherwise}
-    \end{cases}
-$$
+..  math::
 
+    out = \begin{cases}
+             x,  \text{if } x > threshold \\
+             0,  \text{otherwise}
+          \end{cases}
 )DOC");
   }
 };
@@ -444,7 +443,7 @@ class SwishOpMaker : public framework::OpProtoAndCheckerMaker {
     AddComment(R"DOC(
 Swish Activation Operator.
 
-$$out = \frac{x}{1 + e^{- \beta x}}$$
+$$out = \\frac{x}{1 + e^{- \beta x}}$$
 
 )DOC");
   }

paddle/fluid/operators/compare_op.cc

@@ -23,30 +23,26 @@ class CompareOpProtoMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
     OpComment comment;
-    AddInput("X",
-             string::Sprintf("(LoDTensor) the left hand operand of %s operator",
-                             comment.type));
-    AddInput("Y", string::Sprintf(
-                      "(LoDTensor) the right hand operand of %s operator",
-                      comment.type));
+    AddInput("X", string::Sprintf("the left hand operand of %s operator",
+                                  comment.type));
+    AddInput("Y", string::Sprintf("the right hand operand of %s operator",
+                                  comment.type));
     AddAttr<bool>("force_cpu",
-                  "(bool, default false) Force fill output variable to cpu "
+                  "Force fill output variable to cpu "
                   "memory. Otherwise, fill output variable to the running "
-                  "device")
-        .SetDefault(false);
-    AddOutput("Out", string::Sprintf(
-                         "(LoDTensor) n-dim bool tensor. Each element is %s",
-                         comment.equation));
-    AddComment(string::Sprintf(R"DOC(%s Operator
-
+                  "device [default true].")
+        .SetDefault(true);
+    AddOutput("Out", string::Sprintf("n-dim bool tensor. Each element is %s",
+                                     comment.equation));
+    AddComment(string::Sprintf(R"DOC(
 It operates element-wise on X and Y, and returns the Out. Each of them is a
 N-dim tensor. X and Y could be any type.  The each element of the Out tensor is
-calculated by %s
+calculated by $%s$
 )DOC",
-                               comment.type, comment.equation));
-    AddAttr<int>("axis",
-                 "(int, default -1). The start dimension index "
-                 "for broadcasting Y onto X.")
+                               comment.equation));
+    AddAttr<int>(
+        "axis",
+        "The start dimension index for broadcasting Y onto X. [default -1]")
         .SetDefault(-1)
         .EqualGreaterThan(-1);
   }

paddle/fluid/operators/concat_op.cc

@@ -107,7 +107,13 @@ REGISTER_OPERATOR(concat, ops::ConcatOp, ops::ConcatOpMaker,
                       false> /* set false to disable empty grad */);
 REGISTER_OPERATOR(concat_grad, ops::ConcatOpGrad);
 REGISTER_OP_CPU_KERNEL(
-    concat, ops::ConcatKernel<paddle::platform::CPUDeviceContext, float>);
+    concat, ops::ConcatKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, int64_t>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, int>);
 REGISTER_OP_CPU_KERNEL(
     concat_grad,
-    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, float>);
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, int64_t>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, int>);

paddle/fluid/operators/concat_op.cu.cc

@@ -15,7 +15,13 @@ limitations under the License. */
 #include "paddle/fluid/operators/concat_op.h"
 namespace ops = paddle::operators;
 REGISTER_OP_CUDA_KERNEL(
-    concat, ops::ConcatKernel<paddle::platform::CUDADeviceContext, float>);
+    concat, ops::ConcatKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, int64_t>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, int>);
 REGISTER_OP_CUDA_KERNEL(
     concat_grad,
-    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, float>);
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, int64_t>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, int>);

paddle/fluid/operators/crop_op.h

@@ -52,7 +52,7 @@ static std::vector<int> GetOffsets(const framework::ExecutionContext& ctx) {
   } else {
     res = ctx.Attr<std::vector<int>>("offsets");
     PADDLE_ENFORCE_EQ(
-        rank, res.size(),
+        rank, static_cast<int>(res.size()),
         "Offsets size should be equal to dimension size of input tensor.");
   }
   return res;