Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_python35_CI_random_fail

fix-develop-build.sh
minqiyang 7 years ago
commit 3420c94994

@ -53,7 +53,7 @@ RUN curl -s -q https://glide.sh/get | sh
# and its size is only one-third of the official one.
# 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
# See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
RUN wget -qO- http://paddlepaddledeps.bj.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
RUN wget -qO- http://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
tar -xz -C /usr/local && \
cp -rf /usr/local/TensorRT/include /usr && \
cp -rf /usr/local/TensorRT/lib /usr

@ -76,33 +76,26 @@ pip install paddlepaddle-gpu==0.14.0.post85
## Installation
It is recommended to check out the
[Docker installation guide](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/build_and_install/docker_install_en.html)
before looking into the
[build from source guide](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/build_and_install/build_from_source_en.html).
It is recommended to read [this doc](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/beginners_guide/install/install_doc.html) on our website.
## Documentation
We provide [English](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/index_en.html) and
[Chinese](http://www.paddlepaddle.org/docs/develop/documentation/zh/getstarted/index_cn.html) documentation.
We provide [English](http://paddlepaddle.org/documentation/docs/en/0.14.0/getstarted/index_en.html) and
[Chinese](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/beginners_guide/index.html) documentation.
- [Deep Learning 101](http://www.paddlepaddle.org/docs/develop/book/01.fit_a_line/index.html)
- [Deep Learning 101](https://github.com/PaddlePaddle/book)
You might want to start from this online interactive book that can run in a Jupyter Notebook.
- [Distributed Training](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/cluster/index_en.html)
- [Distributed Training](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/user_guides/howto/training/cluster_howto.html)
You can run distributed training jobs on MPI clusters.
- [Distributed Training on Kubernetes](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/cluster/multi_cluster/k8s_en.html)
You can also run distributed training jobs on Kubernetes clusters.
- [Python API](http://www.paddlepaddle.org/docs/develop/api/en/overview.html)
- [Python API](http://paddlepaddle.org/documentation/api/zh/0.14.0/fluid.html)
Our new API enables much shorter programs.
- [How to Contribute](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/dev/contribute_to_paddle_en.html)
- [How to Contribute](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/advanced_usage/development/contribute_to_paddle.html)
We appreciate your contributions!

@ -169,14 +169,19 @@ set(CUDA_PROPAGATE_HOST_FLAGS OFF)
# Release/Debug flags set by cmake. Such as -O3 -g -DNDEBUG etc.
# So, don't set these flags here.
if (NOT WIN32) # windows msvc2015 support c++11 natively.
# -std=c++11 -fPIC not recoginize by msvc, -Xcompiler will be added by cmake.
list(APPEND CUDA_NVCC_FLAGS "-std=c++11")
list(APPEND CUDA_NVCC_FLAGS "--use_fast_math")
list(APPEND CUDA_NVCC_FLAGS "-Xcompiler -fPIC")
endif(NOT WIN32)
list(APPEND CUDA_NVCC_FLAGS "--use_fast_math")
# in cuda9, suppress cuda warning on eigen
list(APPEND CUDA_NVCC_FLAGS "-w")
# Set :expt-relaxed-constexpr to suppress Eigen warnings
list(APPEND CUDA_NVCC_FLAGS "--expt-relaxed-constexpr")
if (NOT WIN32)
if(CMAKE_BUILD_TYPE STREQUAL "Debug")
list(APPEND CUDA_NVCC_FLAGS ${CMAKE_CXX_FLAGS_DEBUG})
elseif(CMAKE_BUILD_TYPE STREQUAL "Release")
@ -187,6 +192,13 @@ elseif(CMAKE_BUILD_TYPE STREQUAL "MinSizeRel")
# nvcc 9 does not support -Os. Use Release flags instead
list(APPEND CUDA_NVCC_FLAGS ${CMAKE_CXX_FLAGS_RELEASE})
endif()
else(NOT WIN32)
if(CMAKE_BUILD_TYPE STREQUAL "Release")
list(APPEND CUDA_NVCC_FLAGS "-O3 -DNDEBUG")
else()
message(FATAL "Windows only support Release build now. Please set visual studio build type to Release, x64 build.")
endif()
endif(NOT WIN32)
mark_as_advanced(CUDA_BUILD_CUBIN CUDA_BUILD_EMULATION CUDA_VERBOSE_BUILD)
mark_as_advanced(CUDA_SDK_ROOT_DIR CUDA_SEPARABLE_COMPILATION)

@ -44,7 +44,7 @@ ExternalProject_Add(
# 3. keep only zlib, cares, protobuf, boringssl under "third_party",
# checkout and clean other dirs under third_party
# 4. remove .git, and package the directory.
URL "http://paddlepaddledeps.bj.bcebos.com/grpc-v1.10.x.tar.gz"
URL "http://paddlepaddledeps.cdn.bcebos.com/grpc-v1.10.x.tar.gz"
URL_MD5 "1f268a2aff6759839dccd256adcc91cf"
PREFIX ${GRPC_SOURCES_DIR}
UPDATE_COMMAND ""

@ -128,16 +128,13 @@ set(src_dir "${PADDLE_SOURCE_DIR}/paddle/fluid")
set(dst_dir "${FLUID_INSTALL_DIR}/paddle/fluid")
set(module "framework")
if (NOT WIN32)
copy(framework_lib DEPS framework_py_proto
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/details/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/framework/framework.pb.h
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module}
)
else()
copy(framework_lib
set(framework_lib_deps framework_py_proto)
endif(NOT WIN32)
copy(framework_lib DEPS ${framework_lib_deps}
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/details/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/framework/framework.pb.h
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module}
${src_dir}/${module}/ir/*.h
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module} ${dst_dir}/${module}/ir
)
endif(NOT WIN32)
set(module "memory")
copy(memory_lib
@ -161,7 +158,8 @@ set(module "inference")
copy(inference_lib DEPS ${inference_deps}
SRCS ${src_dir}/${module}/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/inference/libpaddle_fluid.*
${src_dir}/${module}/api/paddle_inference_api.h ${src_dir}/${module}/api/demo_ci
DSTS ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module}
${PADDLE_BINARY_DIR}/paddle/fluid/inference/api/paddle_inference_pass.h
DSTS ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module}
)
set(module "platform")

@ -1,5 +1,5 @@
服务器端部署 - Anakin
#####################
Anakin - 服务器端加速引擎
#######################
使用文档

@ -1,8 +0,0 @@
服务器端部署 - 原生引擎
#######################
.. toctree::
:maxdepth: 2
build_and_install_lib_cn.rst
native_infer.rst

@ -10,7 +10,6 @@
.. toctree::
:maxdepth: 2
deploy/index_native.rst
deploy/index_anakin.rst
deploy/index_mobile.rst
development/contribute_to_paddle.md

@ -0,0 +1,8 @@
*.pyc
train.log
output
data/cifar-10-batches-py/
data/cifar-10-python.tar.gz
data/*.txt
data/*.list
data/mean.meta

@ -21,7 +21,7 @@
图像分类包括通用图像分类、细粒度图像分类等。图1展示了通用图像分类效果即模型可以正确识别图像上的主要物体。
<p align="center">
<img src="image/dog_cat.png " width="350" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/dog_cat.png?raw=true" width="350" ><br/>
图1. 通用图像分类展示
</p>
@ -30,7 +30,7 @@
<p align="center">
<img src="image/flowers.png" width="400" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/flowers.png?raw=true" width="400" ><br/>
图2. 细粒度图像分类展示
</p>
@ -38,7 +38,7 @@
一个好的模型既要对不同类别识别正确,同时也应该能够对不同视角、光照、背景、变形或部分遮挡的图像正确识别(这里我们统一称作图像扰动)。图3展示了一些图像的扰动较好的模型会像聪明的人类一样能够正确识别。
<p align="center">
<img src="image/variations.png" width="550" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/variations.png?raw=true" width="550" ><br/>
图3. 扰动图片展示[22]
</p>
@ -61,7 +61,7 @@
Alex Krizhevsky在2012年ILSVRC提出的CNN模型 \[[9](#参考文献)\] 取得了历史性的突破效果大幅度超越传统方法获得了ILSVRC2012冠军该模型被称作AlexNet。这也是首次将深度学习用于大规模图像分类中。从AlexNet之后涌现了一系列CNN模型不断地在ImageNet上刷新成绩如图4展示。随着模型变得越来越深以及精妙的结构设计Top-5的错误率也越来越低降到了3.5%附近。而在同样的ImageNet数据集上人眼的辨识错误率大概在5.1%,也就是目前的深度学习模型的识别能力已经超过了人眼。
<p align="center">
<img src="image/ilsvrc.png" width="500" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/ilsvrc.png?raw=true" width="500" ><br/>
图4. ILSVRC图像分类Top-5错误率
</p>
@ -70,7 +70,7 @@ Alex Krizhevsky在2012年ILSVRC提出的CNN模型 \[[9](#参考文献)\] 取得
传统CNN包含卷积层、全连接层等组件并采用softmax多类别分类器和多类交叉熵损失函数一个典型的卷积神经网络如图5所示我们先介绍用来构造CNN的常见组件。
<p align="center">
<img src="image/lenet.png"><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/lenet.png?raw=true"><br/>
图5. CNN网络示例[20]
</p>
@ -89,7 +89,7 @@ Alex Krizhevsky在2012年ILSVRC提出的CNN模型 \[[9](#参考文献)\] 取得
牛津大学VGG(Visual Geometry Group)组在2014年ILSVRC提出的模型被称作VGG模型 \[[11](#参考文献)\] 。该模型相比以往模型进一步加宽和加深了网络结构它的核心是五组卷积操作每两组之间做Max-Pooling空间降维。同一组内采用多次连续的3X3卷积卷积核的数目由较浅组的64增多到最深组的512同一组内的卷积核数目是一样的。卷积之后接两层全连接层之后是分类层。由于每组内卷积层的不同有11、13、16、19层这几种模型下图展示一个16层的网络结构。VGG模型结构相对简洁提出之后也有很多文章基于此模型进行研究如在ImageNet上首次公开超过人眼识别的模型\[[19](#参考文献)\]就是借鉴VGG模型的结构。
<p align="center">
<img src="image/vgg16.png" width="750" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/vgg16.png?raw=true" width="750" ><br/>
图6. 基于ImageNet的VGG16模型
</p>
@ -106,7 +106,7 @@ NIN模型主要有两个特点
Inception模块如下图7所示图(a)是最简单的设计输出是3个卷积层和一个池化层的特征拼接。这种设计的缺点是池化层不会改变特征通道数拼接后会导致特征的通道数较大经过几层这样的模块堆积后通道数会越来越大导致参数和计算量也随之增大。为了改善这个缺点图(b)引入3个1x1卷积层进行降维所谓的降维就是减少通道数同时如NIN模型中提到的1x1卷积也可以修正线性特征。
<p align="center">
<img src="image/inception.png" width="800" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/inception.png?raw=ture" width="800" ><br/>
图7. Inception模块
</p>
@ -115,7 +115,7 @@ GoogleNet由多组Inception模块堆积而成。另外在网络最后也没
GoogleNet整体网络结构如图8所示总共22层网络开始由3层普通的卷积组成接下来由三组子网络组成第一组子网络包含2个Inception模块第二组包含5个Inception模块第三组包含2个Inception模块然后接均值池化层、全连接层。
<p align="center">
<img src="image/googlenet.jpeg" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/googlenet.jpeg?raw=true" ><br/>
图8. GoogleNet[12]
</p>
@ -130,14 +130,14 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
残差模块如图9所示左边是基本模块连接方式由两个输出通道数相同的3x3卷积组成。右边是瓶颈模块(Bottleneck)连接方式之所以称为瓶颈是因为上面的1x1卷积用来降维(图示例即256->64)下面的1x1卷积用来升维(图示例即64->256)这样中间3x3卷积的输入和输出通道数都较小(图示例即64->64)。
<p align="center">
<img src="image/resnet_block.jpg" width="400"><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/resnet_block.jpg?raw=true" width="400"><br/>
图9. 残差模块
</p>
图10展示了50、101、152层网络连接示意图使用的是瓶颈模块。这三个模型的区别在于每组中残差模块的重复次数不同(见图右上角)。ResNet训练收敛较快成功的训练了上百乃至近千层的卷积神经网络。
<p align="center">
<img src="image/resnet.png"><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/resnet.png?raw=true"><br/>
图10. 基于ImageNet的ResNet模型
</p>
@ -149,7 +149,7 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
由于ImageNet数据集较大下载和训练较慢为了方便大家学习我们使用[CIFAR10](<https://www.cs.toronto.edu/~kriz/cifar.html>)数据集。CIFAR10数据集包含60,000张32x32的彩色图片10个类别每个类包含6,000张。其中50,000张图片作为训练集10000张作为测试集。图11从每个类别中随机抽取了10张图片展示了所有的类别。
<p align="center">
<img src="image/cifar.png" width="350"><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/cifar.png?raw=true" width="350"><br/>
图11. CIFAR10数据集[21]
</p>
@ -377,7 +377,7 @@ test_reader = paddle.batch(
`event_handler_plot`可以用来利用回调数据来打点画图:
<p align="center">
<img src="image/train_and_test.png" width="350"><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/train_and_test.png?raw=true" width="350"><br/>
图12. 训练结果
</p>
@ -469,7 +469,7 @@ Test with Pass 0, Loss 1.1, Acc 0.6
图13是训练的分类错误率曲线图运行到第200个pass后基本收敛最终得到测试集上分类错误率为8.54%。
<p align="center">
<img src="image/plot.png" width="400" ><br/>
<img src="https://github.com/PaddlePaddle/book/blob/develop/03.image_classification/image/plot.png?raw=true" width="400" ><br/>
图13. CIFAR10数据集上VGG模型的分类错误率
</p>

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.2 MiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.7 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 413 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 482 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 108 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 436 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 34 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 216 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 226 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 130 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 136 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 109 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 96 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 171 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 54 KiB

Some files were not shown because too many files have changed in this diff Show More

Loading…
Cancel
Save