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

wangkuiyi-patch-1
fengjiayi 7 years ago
commit d684b49cb0

@ -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 |

@ -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

@ -342,6 +342,12 @@ conv2d
.. autofunction:: paddle.fluid.layers.conv2d
:noindex:
conv3d
------
.. autofunction:: paddle.fluid.layers.conv3d
:noindex:
sequence_pool
-------------
@ -366,6 +372,12 @@ pool2d
.. autofunction:: paddle.fluid.layers.pool2d
:noindex:
pool3d
------
.. autofunction:: paddle.fluid.layers.pool3d
:noindex:
batch_norm
----------
@ -384,6 +396,13 @@ conv2d_transpose
.. autofunction:: paddle.fluid.layers.conv2d_transpose
:noindex:
conv3d_transpose
----------------
.. autofunction:: paddle.fluid.layers.conv2d_transpose
:noindex:
sequence_expand
---------------

@ -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

@ -50,7 +50,7 @@ cc_test(test_paddle_inference_api
inference_api_test(test_paddle_inference_api_impl
ARGS test_word2vec test_image_classification)
if (WITH_ANAKIN)
if (WITH_ANAKIN AND WITH_TESTING) # only needed in CI
# Due to Anakin do not have official library releases and the versions of protobuf and cuda do not match Paddle's,
# so anakin library will not be merged to our official inference library. To use anakin prediction API, one need to
# compile the libinference_anakin_api.a and compile with anakin.so.

@ -17,7 +17,7 @@ if(APPLE)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-error=pessimizing-move")
endif(APPLE)
cc_library(tape_variable SRCS variable.cc DEPS ${FLUID_CORE_MODULES})
cc_library(tape_variable SRCS variable.cc DEPS ${FLUID_CORE_MODULES} device_context framework_proto proto_desc operator)
cc_library(tape SRCS tape.cc DEPS ${FLUID_CORE_MODULES} ${GLOB_OP_LIB} tape_variable)
cc_test(test_tape

@ -18,6 +18,7 @@ limitations under the License. */
#include "paddle/fluid/framework/init.h"
#include "paddle/fluid/framework/operator.h"
#include "paddle/fluid/operators/math/blas.h"
#include "paddle/fluid/platform/device_context.h"
#include "paddle/fluid/platform/place.h"
#include "paddle/fluid/string/piece.h"
@ -113,6 +114,9 @@ void InitDevices(bool init_p2p, const std::vector<int> devices) {
}
places.emplace_back(platform::CPUPlace());
platform::DeviceContextPool::Init(places);
#ifndef PADDLE_WITH_MKLDNN
operators::math::SetNumThreads(1);
#endif
}
void InitGLOG(const std::string &prog_name) {

@ -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>);

@ -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>);

@ -85,7 +85,7 @@ class GetPlacesOpProtoMaker : public framework::OpProtoAndCheckerMaker {
.InEnum({"CUDA", "CPU", "AUTO"})
.SetDefault("AUTO");
AddComment(R"DOC(
Returns a list of places based on flags. The list will be used for parallel
Returns a list of places based on arguments. The list will be used for parallel
execution.
)DOC");
}

@ -115,4 +115,7 @@ USE_CPU_ONLY_OP(concat);
REGISTER_OPERATOR(split, ops::SplitOp, ops::SplitOpMaker, ops::SplitGradMaker);
REGISTER_OP_CPU_KERNEL(split,
ops::SplitOpKernel<paddle::platform::CPUPlace, float>);
ops::SplitOpKernel<paddle::platform::CPUPlace, double>,
ops::SplitOpKernel<paddle::platform::CPUPlace, float>,
ops::SplitOpKernel<paddle::platform::CPUPlace, int64_t>,
ops::SplitOpKernel<paddle::platform::CPUPlace, int>);

@ -15,4 +15,7 @@ limitations under the License. */
#include "paddle/fluid/operators/split_op.h"
namespace ops = paddle::operators;
REGISTER_OP_CUDA_KERNEL(
split, ops::SplitOpKernel<paddle::platform::CUDADeviceContext, float>);
split, ops::SplitOpKernel<paddle::platform::CUDADeviceContext, double>,
ops::SplitOpKernel<paddle::platform::CUDADeviceContext, float>,
ops::SplitOpKernel<paddle::platform::CUDADeviceContext, int64_t>,
ops::SplitOpKernel<paddle::platform::CUDADeviceContext, int>);

@ -1224,6 +1224,34 @@ class IfElseBlockGuard(object):
class IfElse(object):
"""
if-else control flow.
Args:
cond (Variable): condition used to compare.
name (str, default None): The name of this layer.
Examples:
.. code-block:: python
limit = fluid.layers.fill_constant_batch_size_like(
input=label, dtype='int64', shape=[1], value=5.0)
cond = fluid.layers.less_than(x=label, y=limit)
ie = fluid.layers.IfElse(cond)
with ie.true_block():
true_image = ie.input(image)
hidden = fluid.layers.fc(input=true_image, size=100, act='tanh')
prob = fluid.layers.fc(input=hidden, size=10, act='softmax')
ie.output(prob)
with ie.false_block():
false_image = ie.input(image)
hidden = fluid.layers.fc(
input=false_image, size=200, act='tanh')
prob = fluid.layers.fc(input=hidden, size=10, act='softmax')
ie.output(prob)
prob = ie()
"""
OUT_IF_ELSE_BLOCKS = 0
IN_IF_ELSE_TRUE_BLOCKS = 1
IN_IF_ELSE_FALSE_BLOCKS = 2

@ -648,6 +648,26 @@ def read_file(reader):
class Preprocessor(object):
"""
A block for data pre-processing in reader.
Args:
reader (Variable): A reader variable.
name (str, default None): The name of the reader.
Examples:
.. code-block:: python
preprocessor = fluid.layers.io.Preprocessor(reader=reader)
with preprocessor.block():
img, lbl = preprocessor.inputs()
img_out = img / 2
lbl_out = lbl + 1
preprocessor.outputs(img_out, lbl_out)
data_file = fluid.layers.io.double_buffer(preprocessor())
"""
BEFORE_SUB_BLOCK = 0
IN_SUB_BLOCK = 1
AFTER_SUB_BLOCK = 2

File diff suppressed because it is too large Load Diff

@ -76,8 +76,7 @@ def db_lstm(word, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark,
emb_layers.append(mark_embedding)
hidden_0_layers = [
fluid.layers.fc(input=emb, size=hidden_dim, act='tanh')
for emb in emb_layers
fluid.layers.fc(input=emb, size=hidden_dim) for emb in emb_layers
]
hidden_0 = fluid.layers.sums(input=hidden_0_layers)
@ -94,8 +93,8 @@ def db_lstm(word, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark,
for i in range(1, depth):
mix_hidden = fluid.layers.sums(input=[
fluid.layers.fc(input=input_tmp[0], size=hidden_dim, act='tanh'),
fluid.layers.fc(input=input_tmp[1], size=hidden_dim, act='tanh')
fluid.layers.fc(input=input_tmp[0], size=hidden_dim),
fluid.layers.fc(input=input_tmp[1], size=hidden_dim)
])
lstm = fluid.layers.dynamic_lstm(

@ -41,8 +41,8 @@ function(py_test_modules TARGET_NAME)
endfunction()
list(REMOVE_ITEM TEST_OPS test_warpctc_op)
list(REMOVE_ITEM TEST_OPS test_dist_train)
#list(REMOVE_ITEM TEST_OPS test_parallel_executor_crf)
#list(REMOVE_ITEM TEST_OPS test_parallel_executor_fetch_feed)
list(REMOVE_ITEM TEST_OPS test_parallel_executor_crf)
list(REMOVE_ITEM TEST_OPS test_parallel_executor_fetch_feed)
# TODO(wuyi): this test hungs on CI, will add it back later
list(REMOVE_ITEM TEST_OPS test_listen_and_serv_op)
foreach(TEST_OP ${TEST_OPS})
@ -50,3 +50,5 @@ foreach(TEST_OP ${TEST_OPS})
endforeach(TEST_OP)
py_test_modules(test_warpctc_op MODULES test_warpctc_op ENVS FLAGS_warpctc_dir=${WARPCTC_LIB_DIR} SERIAL)
py_test_modules(test_dist_train MODULES test_dist_train SERIAL)
py_test_modules(test_parallel_executor_crf MODULES test_parallel_executor_crf SERIAL)
py_test_modules(test_parallel_executor_fetch_feed MODULES test_parallel_executor_fetch_feed SERIAL)

Loading…
Cancel
Save