提交 5b322835 编写于 作者: L liaogang

fix conflicts

上级 4f837b9f d08f7084
develop 1.8.5 2.0.1-rocm-post 2.4.1 Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_kylinv10 add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease bugfix-eval-frame-leakgae cherry-pick-fix-customOP-random-fail cherry_undefined_var compile_windows cp_2.4_fix_numpy delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix-run-program-grad-node-mem fix_check fix_concat_slice fix_custom_device_copy_sync fix_dataloader_memory_leak fix_dlpack_for fix_imperative_dygraph_error fix_newexe_gc fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fix_var_stop_gradient_error fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 hack_event improve_sccache incuabte/new_frl incubate/frl_train_eval incubate/infrt incubate/lite incubate/new_frl incubate/new_frl_rc incubate/stride inplace_addto layer_norm make_flag_adding_easier master matmul_double_grad move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel operator_opt paddle_tiny_install paralleltest pass-compile-eval-frame preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 prv-reshape-mkldnn-ut2 pten_tensor_refactor release-deleted/2.5 release-rc/2.5 release/0.11.0 release/0.12.0 release/0.13.0 release/0.14.0 release/0.15.0 release/1.0.0 release/1.1 release/1.2 release/1.3 release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/2.5 release/lite-0.1 release/llm_2.5 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment revert-47325-remove_cudnn_hardcode revert-47645-add_npu_storage_dims revert-48815-set_free_when_no_cache_hit_default_value_true revert-49499-test_ninja_on_ci revert-49654-prim_api_gen revert-49673-modify_get_single_cov revert-49763-fix_static_composite_gen revert-50158-fix_found_inf_bug_for_custom_optimizer revert-50188-refine_optimizer_create_accumulators revert-50335-fix_optminizer_set_auxiliary_var_bug revert-51676-flag_delete revert-51850-fix_softmaxce_dev revert-52175-dev_peak_memory revert-52186-deve revert-52523-test_py38 revert-52912-develop revert-53248-set_cmake_policy revert-54029-fix_windows_compile_bug revert-54068-support_translating_op_attribute revert-54214-modify_cmake_dependencies revert-54370-offline_pslib revert-54391-fix_cmake_md5error revert-54411-fix_cpp17_compile revert-54466-offline_pslib revert-54480-cmake-rocksdb revert-55568-fix_BF16_bug1 revert-56328-new_ir_support_vector_type_place_transfer revert-56366-fix_openssl_bug revert-56545-revert-56366-fix_openssl_bug revert-56620-fix_new_ir_ocr_bug revert-56925-check_inputs_grad_semantic revert-57005-refine_stride_flag rocm_dev_0217 sd_conv_linear_autocast semi-auto/rule-base support-0D-sort support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_for_Filtetfiles test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.5.1 v2.5.0 v2.5.0-rc1 v2.5.0-rc0 v2.4.2 v2.4.1 v2.4.0 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 v1.3.2 v1.3.1 v1.3.0 v1.2.1 v1.2.0 v1.1.0 v1.0.2 v1.0.1 v1.0.0 v1.0.0-rc0 v0.15.0 v0.15.0-rc0 v0.14.0 v0.13.0 v0.12.0 v0.11.1a2 v0.11.1a1 v0.11.0 lite-v0.1
7 合并请求!11636[IMPORTANT] MKLDNN layout: Support for sum operator,!8482Release/0.11.0,!8190Release/0.11.0,!8189Release/0.11.0,!6633给线性回归的get-started代码加上了预测的示例~~,!4615Feature/tensor array add python binding,!2182add go_xxx to simplify cmake
......@@ -57,8 +57,11 @@ function(cc_binary TARGET_NAME)
set(multiValueArgs SRCS DEPS)
cmake_parse_arguments(cc_binary "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
add_executable(${TARGET_NAME} ${cc_binary_SRCS})
add_dependencies(${TARGET_NAME} ${cc_binary_DEPS} ${external_project_dependencies})
target_link_libraries(${TARGET_NAME} ${cc_binary_DEPS} ${CMAKE_THREAD_LIBS_INIT})
link_paddle_exe(${TARGET_NAME})
if(cc_binary_DEPS)
target_link_libraries(${TARGET_NAME} ${cc_binary_DEPS})
add_dependencies(${TARGET_NAME} ${cc_binary_DEPS})
endif()
endfunction(cc_binary)
# The dependency to target tensor implies that if any of
......@@ -74,12 +77,11 @@ function(cc_test TARGET_NAME)
set(multiValueArgs SRCS DEPS)
cmake_parse_arguments(cc_test "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
add_executable(${TARGET_NAME} ${cc_test_SRCS})
add_dependencies(${TARGET_NAME} ${cc_test_DEPS} ${external_project_dependencies})
target_link_libraries(${TARGET_NAME}
${cc_test_DEPS}
${GTEST_MAIN_LIBRARIES}
${GTEST_LIBRARIES}
${CMAKE_THREAD_LIBS_INIT})
link_paddle_test(${TARGET_NAME})
if(cc_test_DEPS)
target_link_libraries(${TARGET_NAME} ${cc_test_DEPS})
add_dependencies(${TARGET_NAME} ${cc_test_DEPS})
endif()
add_test(${TARGET_NAME} ${TARGET_NAME})
endfunction(cc_test)
......@@ -110,8 +112,11 @@ function(nv_binary TARGET_NAME)
set(multiValueArgs SRCS DEPS)
cmake_parse_arguments(nv_binary "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
cuda_add_executable(${TARGET_NAME} ${nv_binary_SRCS})
add_dependencies(${TARGET_NAME} ${nv_binary_DEPS} ${external_project_dependencies})
target_link_libraries(${TARGET_NAME} ${nv_binary_DEPS} ${CMAKE_THREAD_LIBS_INIT})
link_paddle_exe(${TARGET_NAME})
if(nv_binary_DEPS)
target_link_libraries(${TARGET_NAME} ${nv_binary_DEPS})
add_dependencies(${TARGET_NAME} ${nv_binary_DEPS})
endif()
endfunction(nv_binary)
# The dependency to target tensor implies that if any of
......@@ -127,12 +132,11 @@ function(nv_test TARGET_NAME)
set(multiValueArgs SRCS DEPS)
cmake_parse_arguments(nv_test "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
cuda_add_executable(${TARGET_NAME} ${nv_test_SRCS})
add_dependencies(${TARGET_NAME} ${nv_test_DEPS} ${external_project_dependencies})
target_link_libraries(${TARGET_NAME}
${nv_test_DEPS}
${GTEST_MAIN_LIBRARIES}
${GTEST_LIBRARIES}
${CMAKE_THREAD_LIBS_INIT})
link_paddle_test(${TARGET_NAME})
if(nv_test_DEPS)
target_link_libraries(${TARGET_NAME} ${nv_test_DEPS})
add_dependencies(${TARGET_NAME} ${nv_test_DEPS})
endif()
add_test(${TARGET_NAME} ${TARGET_NAME})
endfunction(nv_test)
......
# 构建Android平台上的PaddlePaddle库
用户可通过交叉编译的方式,在用户熟悉的开发平台(Linux,Mac OS X和Windows)上编译Android平台上适用的PaddlePaddle库。
本文档将以Linux x86-64平台为例,介绍交叉编译Android平台上适用的PaddlePaddle库的方法和步骤。
## 准备交叉编译环境
从源码交叉编译PaddlePaddle,用户需要提前准备好交叉编译环境。Android平台上使用的C/C++交叉编译工具链为[Android NDK](https://developer.android.com/ndk/downloads/index.html?hl=zh-cn),用户可自行前往下载预编译好的版本,也可通过以下命令获取:
```bash
wget -q https://dl.google.com/android/repository/android-ndk-r14b-linux-x86_64.zip
unzip -q android-ndk-r14b-linux-x86_64.zip
```
Android NDK中包含了所有Android API级别、所有架构(arm/arm64/x86/mips)需要用到的编译工具和系统库。用户可根据自己的编译目标架构、所需支持的最低Android API级别,构建[独立工具链](https://developer.android.google.cn/ndk/guides/standalone_toolchain.html?hl=zh-cn)
比如:
```bash
your/path/to/android-ndk-r14b-linux-x86_64/build/tools/make-standalone-toolchain.sh \
--arch=arm --platform=android-21 --install-dir=your/path/to/my_standalone_toolchain
```
此命令将在your/path/to/my_standalone_toolchain目录生成一套编译工具链,面向架构为32位ARM架构,支持的最小的Android API级别为21,使用的编译器为arm-linux-androideabi-gcc (GCC) 4.9。
注意:**PaddlePaddle要求使用的编译工具链所支持的Andoid API级别不小于21**
## 配置交叉编译参数
CMake系统对交叉编译提供了支持[cmake-toolchains](https://cmake.org/cmake/help/v3.0/manual/cmake-toolchains.7.html#cross-compiling)。为了简化cmake配置,PaddlePaddle为交叉编译提供了工具链配置文档[cmake/cross_compiling/android.cmake](https://github.com/PaddlePaddle/Paddle/blob/develop/cmake/cross_compiling/android.cmake),以提供一些默认的编译器和编译参数相关配置。注意,从CMake 3.7版本开始,CMake官方对Android平台的交叉编译提供了通用的支持。PaddlePaddle若检测到用户使用的CMake版本不低于3.7时,将会将用户传进来的配置参数传递CMake系统,交由CMake系统本身来处理。有关参数配置的详细说明见[cmake-toolchains](https://cmake.org/cmake/help/v3.7/manual/cmake-toolchains.7.html#cross-compiling)
交叉编译Android版本的PaddlePaddle库时,有一些必须配置的参数:
- `CMAKE_SYSTEM_NAME`,CMake编译的目标平台,必须设置为`Android`。在设置`CMAKE_SYSTEM_NAME=Android`后,PaddlePaddle的CMake系统才认为是在交叉编译Android系统的版本,并自动编译宿主机版protoc可执行文件、目标机版protobuf库、以及Android所需`arm_soft_fp_abi`分支的目标机版OpenBLAS库。此外,还会强制设置一些PaddlePaddle参数的值(`WITH_GPU=OFF``WITH_AVX=OFF``WITH_PYTHON=OFF``WITH_RDMA=OFF`)。
- `WITH_C_API`,必须设置为`ON`。在Android平台上只支持使用C-API来预测。
- `WITH_SWIG_PY`,必须设置为`OFF`。在Android平台上不支持通过swig调用来训练或者预测。
Android平台可选配置参数:
- `ANDROID_STANDALONE_TOOLCHAIN`,独立工具链所在的绝对路径,或者相对于构建目录的相对路径。PaddlePaddle的CMake系统将根据该值自动推导和设置需要使用的交叉编译器、sysroot、以及Android API级别;否则,用户需要在cmake时手动设置这些值。无默认值。
- `ANDROID_ABI`,目标架构ABI。目前只支持`armeabi-v7a`,默认值为`armeabi-v7a`
- `ANDROID_NATIVE_API_LEVEL`,工具链的Android API级别。若没有显式设置,PaddlePaddle将根据`ANDROID_STANDALONE_TOOLCHAIN`的值自动推导得到。
- `ANROID_ARM_MODE`,是否使用ARM模式。可设置`ON/OFF`,默认值为`ON`
- `ANDROID_ARM_NEON`,是否使用NEON指令。目前必须设置成`ON`,默认值为`ON`
其他配置参数:
- `HOST_C/CXX_COMPILER`,宿主机的C/C++编译器。在编译宿主机版protoc可执行文件和目标机版OpenBLAS库时需要用到。默认设置成环境变量`CC`的值;若环境变量`CC`没有设置,则设置成`cc`编译器。
一种常用的cmake配置如下:
```bash
cmake -DCMAKE_SYSTEM_NAME=Android \
-DANDROID_STANDALONE_TOOLCHAIN=your/path/to/my_standalone_toolchain \
-DANDROID_ABI=armeabi-v7a \
-DANDROID_ARM_NEON=ON \
-DANDROID_ARM_MODE=ON \
-DCMAKE_INSTALL_PREFIX=your/path/to/install \
-DWITH_C_API=ON \
-DWITH_SWIG_PY=OFF \
..
```
用户还可根据自己的需求设置其他编译参数。比如希望最小化生成的库的大小,可以设置`CMAKE_BUILD_TYPE``MinSizeRel`;若希望最快的执行速度,则可设置`CMAKE_BUILD_TYPE``Release`。亦可以通过手动设置`CMAKE_C/CXX_FLAGS_MINSIZEREL/RELEASE`来影响PaddlePaddle的编译过程。
## 编译和安装
CMake配置完成后,执行以下命令,PaddlePaddle将自动下载和编译所有第三方依赖库、编译和安装PaddlePaddle预测库。
```bash
make
make install
```
注意:如果你曾经在源码目录下编译过其他平台的PaddlePaddle库,请先使用`rm -rf`命令删除`third_party`目录和`build`目录,以确保所有的第三方依赖库和PaddlePaddle代码都是针对新的CMake配置重新编译的。
执行完安装命令后,`your/path/to/install`目录中会包含`include``lib`目录,其中`include`中包含C-API的头文件,`lib`中包含一个Android版本的库。自此,PaddlePaddle的已经安装完成,用户可将`your/path/to/install`目录下的生成文件用于深度学习相关Android App中,调用方法见C-API文档。
# 构建Raspberry Pi平台上的PaddlePaddle库
对于Rasspberry Pi系统,用户可通过ssh等方式登录到Raspberry Pi系统上,按照[源码编译PaddlePaddle](http://www.paddlepaddle.org/doc_cn/getstarted/build_and_install/cmake/build_from_source_cn.html)相关文档所述,直接编译Raspberry Pi平台上适用的PaddlePaddle库。
用户也可以在自己熟悉的开发平台上,通过交叉编译的方式来编译。这篇文档将以Linux x86-64平台为例,介绍交叉编译Raspberry Pi平台上适用的PaddlePaddle的方法和步骤。
## 准备交叉编译环境
从源码交叉编译PaddlePaddle,用户需要提前准备好交叉编译环境。用户可自行前往[github](https://github.com/raspberrypi/tools)下载Raspberry Pi平台使用的C/C++交叉编译工具链,也可通过以下命令获取:
```bash
git clone https://github.com/raspberrypi/tools.git
```
该github仓库中包含若干个预编译好的、针对不同平台的编译工具。宿主机是Linux x86-64环境,则需选用`arm-bcm2708/gcc-linaro-arm-linux-gnueabihf-raspbian-x64`下的作为编译工具,所使用的编译器为arm-linux-gnueabihf-gcc 4.8.3。
注意,该编译工具链需要系统glibc支持2.14以上。
## 配置交叉编译参数
CMake系统对交叉编译提供了支持[cmake-toolchains](https://cmake.org/cmake/help/v3.0/manual/cmake-toolchains.7.html#cross-compiling)。为了简化cmake配置,PaddlePaddle为交叉编译提供了工具链配置文档[cmake/cross_compiling/raspberry_pi.cmake](https://github.com/PaddlePaddle/Paddle/blob/develop/cmake/cross_compiling/raspberry_pi.cmake),以提供一些默认的编译器和编译参数相关配置。
交叉编译Raspberry Pi版本PaddlePaddle库时,有一些必须配置的参数:
- `CMAKE_SYSTEM_NAME`,CMake编译的目标平台,必须配置为`RPi`。在设置`CMAKE_SYSTEM_NAME=RPi`后,PaddlePaddle的CMake系统才认为在是在交叉编译Raspberry Pi系统的版本,并自动编译宿主机版protoc可执行文件、目标机版protobuf库、以及目标机版OpenBLAS库。
Raspberry Pi平台可选配置参数:
- `RPI_TOOLCHAIN`,编译工具链所在的绝对路径,或者相对于构建目录的相对路径。PaddlePaddle的CMake系统将根据该值自动设置需要使用的交叉编译器;否则,用户需要在cmake时手动设置这些值。无默认值。
- `RPI_ARM_NEON`,是否使用NEON指令。目前必须设置成`ON`,默认值为`ON`
其他配置参数:
- `HOST_C/CXX_COMPILER`,宿主机的C/C++编译器。在编译宿主机版protoc可执行文件和目标机版OpenBLAS库时需要用到。默认设置成环境变量`CC`的值;若环境变量`CC`没有设置,则设置成`cc`编译器。
cmake参数如下;
```
cmake -DCMAKE_SYSTEM_NAME=RPi \
-DRPI_TOOLCHAIN=your/path/to/arm-bcm2708/gcc-linaro-arm-linux-gnueabihf-raspbian-x64 \
-DRPI_ARM_NEON=ON \
-DCMAKE_INSTALL_PREFIX=your/path/to/install \
-DWITH_GPU=OFF \
-DWITH_C_API=ON \
-DWITH_PYTHON=OFF \
-DWITH_SWIG_PY=OFF \
..
```
用户还可根据自己的需求设置其他编译参数。比如希望最小化生成的库的大小,可以设置`CMAKE_BUILD_TYPE``MinSizeRel`;若希望最快的执行速度,则可设置`CMAKE_BUILD_TYPE``Release`。亦可以通过手动设置`CMAKE_C/CXX_FLAGS_MINSIZEREL/RELEASE`来影响PaddlePaddle的编译过程。
## 编译和安装
CMake配置完成后,执行以下命令,PaddlePaddle将自动下载和编译所有第三方依赖库、编译和安装PaddlePaddle。
```bash
make
make install
```
注意:如果你曾经在源码目录下编译过其他平台的PaddlePaddle库,请先使用`rm -rf`命令删除`third_party`目录和`build`目录,以确保所有的第三方依赖库和PaddlePaddle代码都是针对新的CMake配置重新编译的。
执行完安装命令后,由于上一步cmake配置中`WITH_C_API`设置为`ON``your/path/to/install`目录中会包含`include``lib`目录,其中`include`中包含C-API的头文件,`lib`中包含一个Raspberry Pi版本的库。
更多的编译配置见[源码编译PaddlePaddle](http://www.paddlepaddle.org/doc_cn/getstarted/build_and_install/cmake/build_from_source_cn.html)相关文档。
# 如何构建Raspberry pi下运行的PaddlePaddle
这里考虑的是交叉编译方式,即在Linux-x86环境下构建Raspberry pi下可运行的PaddlePaddle。
## 下载交叉编译环境
```
git clone https://github.com/raspberrypi/tools
```
如果host是x86-64环境,选用`arm-bcm2708/gcc-linaro-arm-linux-gnueabihf-raspbian-x64`下的作为编译工具。注意,需要系统glibc支持2.14以上。
## 编译第三方库
cmake编译PaddlePaddle时候会自动下载编译依赖的第三方库,不过openblas和protobuf最好还是在编译PaddlePaddle之前先编译好,这样可以保证编译PaddlePaddle的时候更加顺畅。
### 编译OpenBLAS
```
git clone https://github.com/xianyi/OpenBLAS.git
make TARGET=ARMV7 HOSTCC=gcc CC=arm-linux-gnueabihf-gcc NOFORTRAN=1 USE_THREAD=0
```
### 编译protobuf
```
git clone https://github.com/google/protobuf.git
git checkout 9f75c5aa851cd877fb0d93ccc31b8567a6706546
cmake ../protobuf/cmake \
-Dprotobuf_BUILD_TESTS=OFF \
-DCMAKE_CXX_COMPILER=arm-linux-gnueabihf-g++ \
-DCMAKE_C_COMPILER=arm-linux-gnueabihf-gcc \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_INSTALL_LIBDIR=lib
```
注意:这样编译出来的`libprotobuf.a``protoc`都是ARM版本的,而我们需要的是一个x86-64版本的`protoc`,所以需要用host gcc再编译一遍protobuf然后使用其中的`protoc`
## 编译PaddlePaddle
cmake参数如下;其中`WITH_C_API`设置为ON,编译输出的output目录会中包含`include``lib`目录,其中`include`中包含CAPI的头文件,`lib`中包含一个ARM版本的库。另外,`CMAKE_BUILD_TYPE`设置为`MinSizeRel`可以减小编译的库的大小。
```
cmake .. -DWITH_GPU=OFF -DWITH_C_API=ON -DWITH_PYTHON=OFF -DWITH_SWIG_PY=OFF \
-DCMAKE_CXX_COMPILER:FILEPATH=arm-linux-gnueabihf-g++ \
-DCMAKE_C_COMPILER:FILEPATH=arm-linux-gnueabihf-gcc \
-DCMAKE_C_FLAGS="-mfpu=neon" \
-DCMAKE_CXX_FLAGS="-mfpu=neon" \
-DOPENBLAS_ROOT=openblas \
-DCMAKE_PREFIX_PATH=protobuf \
-DCMAKE_BUILD_TYPE=MinSizeRel
```
......@@ -26,10 +26,7 @@ FILE(GLOB PY_PADDLE_PYTHON_FILES ${PROJ_ROOT}/paddle/py_paddle/*.py)
SET_SOURCE_FILES_PROPERTIES(Paddle.i PROPERTIES CPLUSPLUS ON)
SET(CMAKE_SWIG_OUTDIR ${CMAKE_CURRENT_BINARY_DIR})
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11 -fPIC -Wall")
IF(WITH_COVERAGE)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -g -O0 -fprofile-arcs -ftest-coverage")
ENDIF(WITH_COVERAGE)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-parentheses-equality -Wno-missing-field-initializers -Wno-self-assign")
SET(SWIG_MODULE_swig_paddle_EXTRA_DEPS
paddle_parameter
......
#include "majel/place.h"
#include <sstream>
#include "gtest/gtest.h"
#include "paddle/utils/Logging.h"
TEST(Place, Equality) {
majel::CpuPlace cpu;
......@@ -37,4 +38,5 @@ TEST(Place, Print) {
ss << majel::CpuPlace();
EXPECT_EQ("CpuPlace", ss.str());
}
LOG(INFO) << "\n[----------] Done \n";
}
import numpy as np
try:
import cv2
except ImportError:
cv2 = None
from cv2 import resize
except:
print(
"import cv2 error, please install opencv-python: pip install opencv-python"
)
__all__ = [
"load_image", "resize_short", "to_chw", "center_crop", "random_crop",
......@@ -76,7 +76,7 @@ def resize_short(im, size):
h_new = size * h / w
else:
w_new = size * w / h
im = resize(im, (h_new, w_new), interpolation=cv2.INTER_CUBIC)
im = cv2.resize(im, (h_new, w_new), interpolation=cv2.INTER_CUBIC)
return im
......
......@@ -18,7 +18,6 @@ setup(name='paddle',
"numpy",
"protobuf==${PROTOBUF_VERSION}",
"matplotlib",
"opencv-python",
],
packages=packages,
package_dir={
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部