Merge branch 'develop' into improve-prefetch-on-server

Author: jacquesqiao

.travis.yml

@@ -34,7 +34,7 @@ addons:
       - automake
       - libtool
       - ccache
-  ssh_known_hosts: 52.76.173.135
+  ssh_known_hosts: 13.229.163.131
 before_install:
   - if [[ "$JOB" == "check_style" ]]; then sudo ln -s /usr/bin/clang-format-3.8 /usr/bin/clang-format; fi
   # Paddle is using protobuf 3.1 currently. Protobuf 3.2 breaks the compatibility. So we specify the python

doc/fluid/dev/api_doc_std_en.md

@@ -0,0 +1,226 @@
+# API Doc Standard
+
+- [API Doc Structure](#API Doc Structure)
+- [Format and Examples](#Format and Examples)
+- [Complete Example](#Complete Example)
+
+
+## API Doc Structure
+
+API Doc should contain the following parts(please write them in order):
+
+- Python API Definition
+
+  The definition of API
+
+- Function Description
+
+  Description of API's function. 
+  The description includes: meaning, purpose and operation on input of API, reference and corresponding link(if any), formula(if necessary) and explanations of key variables in the formula.
+
+- Args Description
+
+  Description of API parameters.
+  Introduce parameters one by one according to the order in API definition.
+  The introduction includes: data type, default value(if any), meaning, etc.
+
+- Returns
+
+  Introduction of API returned value.
+  Introduce meaning of returned value, provide correspoding format if necessary.
+  If returned value is a tuple containing multiple parameters, then introduce parameters one by one in order.
+
+- Raises（if any）
+
+   Abnormality, error that may occur, and possible reasons. If there are more than one possible abnormity or error, they should be listed in order. 
+
+- Note（if any）
+
+  Matters needing attention. If there are more than one matters, they should be listed in order. 
+
+- Examples
+
+  Examples of how to use API.
+
+
+## Format and Examples
+
+API documentation must obey reStructuredText format, please refer to [here](http://sphinx-doc-zh.readthedocs.io/en/latest/rest.html).
+Format and examples of each part of API documantation are as follows: (take fc for example)
+
+- Python API Definition
+
+  - Format
+
+      [Python API Definition]
+
+  - Example
+
+      ```
+      fc(input,
+         size,
+         num_flatten_dims=1,
+         param_attr=None,
+         bias_attr=None,
+         act=None,
+         name=None,
+         main_program=None,
+         startup_program=None)
+      ```
+
+- Function Description
+
+  - Format
+
+      This part contains (please write them in order):
+
+      [Function Description]
+
+      [Formula]
+
+      [Symbols' Descriptions if necessary]
+
+      [References if necessary]
+
+  - Example
+
+      [Function Description]
+
+       ```
+       **Fully Connected Layer**
+
+       The fully connected layer can take multiple tensors as its inputs. It
+       creates a variable called weights for each input tensor, which represents
+       a fully connected weight matrix from each input unit to each output unit.
+       The fully connected layer multiplies each input tensor with its coresponding
+       weight to produce an output Tensor. If multiple input tensors are given,
+       the results of multiple multiplications will be sumed up. If bias_attr is
+       not None, a bias variable will be created and added to the output. Finally,
+       if activation is not None, it will be applied to the output as well.
+       ```
+
+      [Formula]
+
+      ```
+      This process can be formulated as follows:
+
+      .. math::
+
+           Out = Act({\sum_{i=0}^{N-1}X_iW_i + b})
+      ```
+
+      [Symbols' Descriptions if necessary]
+
+      ```
+      In the above equation:
+
+      * :math:`N`: Number of the input.
+      * :math:`X_i`: The input tensor.
+      * :math:`W`: The weights created by this layer.
+      * :math:`b`: The bias parameter created by this layer (if needed).
+      * :math:`Act`: The activation function.
+      * :math:`Out`: The output tensor.
+      ```
+
+      [References if necessary]
+
+      Since there is no need for reference of fc, we omit them here. Under other circumstances, please provide explicit reference and link, take layer_norm for example: 
+
+      ```
+      Refer to `Layer Normalization <https://arxiv.org/pdf/1607.06450v1.pdf>`_ for more details.
+      ```
+
+
+- Args Description
+
+  - Format
+
+      \[Arg's Name\][(Data Type, Default Value)][Description]
+
+  - Example
+
+      part of fc parameters are as follows:
+
+      ```
+      Args:
+          input (Variable|list of Variable): The input tensor(s) of this layer, and the dimension of
+              the input tensor(s) is at least 2.
+          param_attr (ParamAttr|list of ParamAttr, default None): The parameter attribute for learnable
+              parameters/weights of this layer.
+          name (str, default None): The name of this layer.
+      ```
+
+- Returns
+
+  - Format
+
+      [Name][Shape]
+
+  - Example
+
+      ```
+      Returns:
+          A tensor variable storing the transformation result.
+      ```
+
+      when returned value contain more than one tuple, please introduce every parameter in order, take dynamic_lstm for example:
+
+      ```
+      Returns:
+          A tuple containing:
+            The hidden state of LSTM whose shape is (T X D).
+            The cell state of LSTM whose shape is (T X D).
+      ```
+
+- Raises
+
+  - Format
+
+      [Exception Type][Condition]
+
+  - Example
+
+      ```
+      Raises:
+          ValueError: If the rank of the input is less than 2.
+      ```
+
+- Note
+
+  - Format
+
+     [Note]
+
+  - Example
+
+      there is no Note in fc, so we omit this part. If there is any note, please write clearly. If there are more than one notes, please list them in order. Take scaled\_dot\_product\_attention for example:
+
+      ```
+      Note:
+          1. When num_heads > 1, three linear projections are learned respectively
+             to map input queries, keys and values into queries', keys' and values'.
+             queries', keys' and values' have the same shapes with queries, keys
+             and values.
+          2. When num_heads == 1, scaled_dot_product_attention has no learnable
+             parameters.
+      ```
+
+- Examples
+
+  - Format
+
+      \[Python Code Snipper]
+
+  - Example
+
+      ```
+      Examples:
+          .. code-block:: python
+
+            data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
+            fc = fluid.layers.fc(input=data, size=1000, act="tanh")
+      ```
+
+## Complete Example
+
+Complete Example of fc please see [here](src/fc.py)。

paddle/fluid/framework/CMakeLists.txt

@@ -104,7 +104,7 @@ cc_test(init_test SRCS init_test.cc DEPS init)
 cc_test(op_kernel_type_test SRCS op_kernel_type_test.cc DEPS place device_context framework_proto)
 cc_test(cow_ptr_tests SRCS details/cow_ptr_test.cc)
 
-# cc_test(channel_test SRCS channel_test.cc)
+cc_test(channel_test SRCS channel_test.cc)
 cc_test(tuple_test SRCS tuple_test.cc )
 cc_test(concurrency_test SRCS concurrency_test.cc DEPS go_op channel_close_op channel_create_op
         channel_send_op channel_recv_op sum_op select_op elementwise_add_op compare_op

paddle/fluid/framework/channel_impl.h

@@ -138,8 +138,8 @@ void ChannelImpl<T>::Send(T *item) {
 
   // If channel is closed, throw exception
   if (closed_) {
-    lock.unlock();
     send_return();
+    lock.unlock();
     PADDLE_THROW("Cannot send on closed channel");
   }
 
@@ -152,11 +152,9 @@ void ChannelImpl<T>::Send(T *item) {
     if (m != nullptr) {
       *(m->data) = std::move(*item);
       m->Notify();
-      lock.unlock();
       send_return();
       return;
     } else {
-      lock.unlock();
       Send(item);
       send_return();
       return;
@@ -169,8 +167,6 @@ void ChannelImpl<T>::Send(T *item) {
   if (buf_.size() < cap_) {
     // Copy to buffer
     buf_.push_back(std::move(*item));
-    // Release lock and return true
-    lock.unlock();
     send_return();
     return;
   }
@@ -181,8 +177,8 @@ void ChannelImpl<T>::Send(T *item) {
   sendq.push_back(m);
   m->Wait(lock);
   if (m->chan_closed) {
-    lock.unlock();
     send_return();
+    lock.unlock();
     PADDLE_THROW("Cannot send on closed channel");
   }
   send_return();
@@ -195,10 +191,7 @@ bool ChannelImpl<T>::Receive(T *item) {
 
   // If channel is closed and buffer is empty or
   // channel is unbuffered
-  if (closed_ && buf_.empty()) {
-    lock.unlock();
-    return recv_return(false);
-  }
+  if (closed_ && buf_.empty()) return recv_return(false);
 
   // If there is a sender, directly receive the value we want
   // from the sender. In case of a buffered channel, read from
@@ -229,7 +222,6 @@ bool ChannelImpl<T>::Receive(T *item) {
       } else
         return recv_return(Receive(item));
     }
-    lock.unlock();
     return recv_return(true);
   }
 
@@ -238,8 +230,7 @@ bool ChannelImpl<T>::Receive(T *item) {
     // Directly read from buffer
     *item = std::move(buf_.front());
     buf_.pop_front();
-    // Release lock and return true
-    lock.unlock();
+    // return true
     return recv_return(true);
   }
 

paddle/fluid/operators/detail/CMakeLists.txt

@@ -2,8 +2,8 @@ if(WITH_DISTRIBUTE)
   grpc_library(sendrecvop_grpc SRCS bytebuffer_stream.cc sendrecvop_utils.cc grpc_client.cc
       grpc_server.cc variable_response.cc PROTO send_recv.proto DEPS lod_tensor selected_rows)
   set(DISTRIBUTE_COMPILE_FLAGS "-Wno-non-virtual-dtor -Wno-error=non-virtual-dtor -Wno-error=delete-non-virtual-dtor")
-  set_source_files_properties(test_serde.cc grpc_server_test.cc PROPERTIES COMPILE_FLAGS ${DISTRIBUTE_COMPILE_FLAGS})
-  cc_test(serde_test SRCS test_serde.cc variable_response.cc DEPS grpc++_unsecure grpc_unsecure gpr
+  set_source_files_properties(serde_test.cc grpc_server_test.cc PROPERTIES COMPILE_FLAGS ${DISTRIBUTE_COMPILE_FLAGS})
+  cc_test(serde_test SRCS serde_test.cc variable_response.cc DEPS grpc++_unsecure grpc_unsecure gpr
       cares zlib protobuf sendrecvop_grpc)
   cc_test(grpc_server_test SRCS grpc_server_test.cc DEPS sendrecvop_grpc grpc++_unsecure grpc_unsecure gpr cares zlib protobuf)
 endif()

paddle/fluid/operators/detail/grpc_server.cc

@@ -156,12 +156,12 @@ class RequestPrefetch final : public RequestBase {
 
   virtual void Process() {
     // prefetch process...
-    ::grpc::ByteBuffer relay;
+    ::grpc::ByteBuffer reply;
     // TODO(Yancey1989): execute the Block which containers prefetch ops
 
     VLOG(3) << "RequestPrefetch Process in";
 
-    responder_.Finish(relay, ::grpc::Status::OK, this);
+    responder_.Finish(reply, ::grpc::Status::OK, this);
     status_ = FINISH;
   }
 

paddle/fluid/operators/detail/test_serde.cc renamed to paddle/fluid/operators/detail/serde_test.cc

@@ -73,12 +73,13 @@ add_custom_target(paddle_python ALL DEPENDS ${paddle_python_deps})
 set(PADDLE_PYTHON_PACKAGE_DIR ${CMAKE_CURRENT_BINARY_DIR}/dist/)
 
 if (WITH_TESTING)
+  add_subdirectory(paddle/reader/tests)
+  add_subdirectory(paddle/dataset/tests)
   if(NOT WITH_FLUID_ONLY)
     add_subdirectory(paddle/trainer_config_helpers/tests)
     if (WITH_SWIG_PY)
       # enable v2 API unittest only when paddle swig api is compiled
       add_subdirectory(paddle/v2/tests)
-      add_subdirectory(paddle/v2/reader/tests)
       add_subdirectory(paddle/v2/plot/tests)
     endif()
   endif()

python/CMakeLists.txt

@@ -14,8 +14,14 @@
 try:
     from version import full_version as __version__
     from version import commit as __git_commit__
+
 except ImportError:
     import sys
     sys.stderr.write('''Warning with import paddle: you should not 
      import paddle from the source directory; please install paddlepaddle*.whl firstly.'''
                      )
+
+import reader
+import dataset
+import batch
+batch = batch.batch