未验证 提交 d77e6a67 编写于 作者: K kexinzhao 提交者: GitHub

Merge pull request #7636 from kexinzhao/save_inference_model

Add feed and fetch op to ProgramDesc before saving for inference
上级 7905e367 856f650a
develop 2.0.1-rocm-post Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease cherry_undefined_var compile_windows 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_concat_slice fix_dataloader_memory_leak fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var 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 improve_sccache incubate/infrt incubate/lite inplace_addto make_flag_adding_easier master 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 paddle_tiny_install paralleltest preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 pten_tensor_refactor 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/lite-0.1 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 rocm_dev_0217 support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 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 lite-v0.1
无相关合并请求
......@@ -8,27 +8,6 @@ cc_library(paddle_fluid_api
# Merge all modules into a simgle static library
cc_library(paddle_fluid DEPS paddle_fluid_api ${FLUID_CORE_MODULES})
# ptools
# just for testing, we may need to change the storing format for inference_model
# and move the dependent of pickle.
# download from http://www.picklingtools.com/
# build in the C++ sub-directory, using command
# make -f Makefile.Linux libptools.so
set(PTOOLS_LIB)
set(PTOOLS_ROOT $ENV{PTOOLS_ROOT} CACHE PATH "Folder contains PicklingTools")
find_path(PTOOLS_INC_DIR chooseser.h PATHS ${PTOOLS_ROOT}/C++)
find_library(PTOOLS_SHARED_LIB NAMES ptools PATHS ${PTOOLS_ROOT}/C++)
if(PTOOLS_INC_DIR AND PTOOLS_SHARED_LIB)
add_definitions(-DPADDLE_USE_PTOOLS)
set(PTOOLS_LIB ptools)
message(STATUS "Found PicklingTools: ${PTOOLS_SHARED_LIB}")
add_library(${PTOOLS_LIB} SHARED IMPORTED GLOBAL)
set_property(TARGET ${PTOOLS_LIB} PROPERTY IMPORTED_LOCATION ${PTOOLS_SHARED_LIB})
include_directories(${PTOOLS_ROOT}/C++)
include_directories(${PTOOLS_ROOT}/C++/opencontainers_1_8_5/include)
add_definitions(-DOC_NEW_STYLE_INCLUDES) # used in ptools
endif()
add_executable(example example.cc)
if(APPLE)
set(OPTIONAL_LINK_FLAGS)
......
......@@ -18,33 +18,21 @@ limitations under the License. */
#include "paddle/inference/inference.h"
DEFINE_string(dirname, "", "Directory of the inference model.");
DEFINE_string(feed_var_names, "", "Names of feeding variables");
DEFINE_string(fetch_var_names, "", "Names of fetching variables");
int main(int argc, char** argv) {
google::ParseCommandLineFlags(&argc, &argv, true);
if (FLAGS_dirname.empty() || FLAGS_feed_var_names.empty() ||
FLAGS_fetch_var_names.empty()) {
if (FLAGS_dirname.empty()) {
// Example:
// ./example --dirname=recognize_digits_mlp.inference.model
// --feed_var_names="x"
// --fetch_var_names="fc_2.tmp_2"
std::cout << "Usage: ./example --dirname=path/to/your/model "
"--feed_var_names=x --fetch_var_names=y"
<< std::endl;
std::cout << "Usage: ./example --dirname=path/to/your/model" << std::endl;
exit(1);
}
std::cout << "FLAGS_dirname: " << FLAGS_dirname << std::endl;
std::cout << "FLAGS_feed_var_names: " << FLAGS_feed_var_names << std::endl;
std::cout << "FLAGS_fetch_var_names: " << FLAGS_fetch_var_names << std::endl;
std::string dirname = FLAGS_dirname;
std::vector<std::string> feed_var_names = {FLAGS_feed_var_names};
std::vector<std::string> fetch_var_names = {FLAGS_fetch_var_names};
paddle::InferenceEngine* engine = new paddle::InferenceEngine();
engine->LoadInferenceModel(dirname, feed_var_names, fetch_var_names);
engine->LoadInferenceModel(dirname);
paddle::framework::LoDTensor input;
srand(time(0));
......
......@@ -25,19 +25,37 @@ limitations under the License. */
namespace paddle {
void InferenceEngine::LoadInferenceModel(const std::string& dirname) {
std::string model_filename = dirname + "/__model__.dat";
LOG(INFO) << "loading model from " << model_filename;
std::ifstream inputfs(model_filename, std::ios::in | std::ios::binary);
std::string program_desc_str;
inputfs.seekg(0, std::ios::end);
program_desc_str.resize(inputfs.tellg());
inputfs.seekg(0, std::ios::beg);
LOG(INFO) << "program_desc_str's size: " << program_desc_str.size();
inputfs.read(&program_desc_str[0], program_desc_str.size());
inputfs.close();
program_ = new framework::ProgramDesc(program_desc_str);
GenerateLoadProgram(dirname);
framework::BlockDesc* global_block = program_->MutableBlock(0);
feed_var_names_.clear();
fetch_var_names_.clear();
for (auto* op : global_block->AllOps()) {
if (op->Type() == "feed") {
feed_var_names_.insert(feed_var_names_.begin(), op->Output("Out")[0]);
} else if (op->Type() == "fetch") {
fetch_var_names_.push_back(op->Input("X")[0]);
}
}
}
void InferenceEngine::LoadInferenceModel(
const std::string& dirname,
const std::vector<std::string>& feed_var_names,
const std::vector<std::string>& fetch_var_names) {
#ifdef PADDLE_USE_PTOOLS
std::string model_filename = dirname + "/__model__";
LOG(INFO) << "Using PicklingTools, loading model from " << model_filename;
Val v;
LoadValFromFile(model_filename.c_str(), v, SERIALIZE_P0);
std::string program_desc_str = v["program_desc_str"];
LOG(INFO) << "program_desc_str's size: " << program_desc_str.size();
// PicklingTools cannot parse the vector of strings correctly.
#else
std::string model_filename = dirname + "/__model__.dat";
LOG(INFO) << "loading model from " << model_filename;
std::ifstream inputfs(model_filename, std::ios::in | std::ios::binary);
......@@ -48,7 +66,7 @@ void InferenceEngine::LoadInferenceModel(
LOG(INFO) << "program_desc_str's size: " << program_desc_str.size();
inputfs.read(&program_desc_str[0], program_desc_str.size());
inputfs.close();
#endif
program_ = new framework::ProgramDesc(program_desc_str);
GenerateLoadProgram(dirname);
......@@ -62,7 +80,7 @@ void InferenceEngine::LoadInferenceModel(
}
bool InferenceEngine::IsParameter(const framework::VarDesc* var) {
if (var->Persistable()) {
if (var->Persistable() && var->Name() != "feed" && var->Name() != "fetch") {
// There are many unreachable variables in the program
for (size_t i = 0; i < program_->Size(); ++i) {
const framework::BlockDesc& block = program_->Block(i);
......
......@@ -28,6 +28,7 @@ public:
delete load_program_;
}
void LoadInferenceModel(const std::string& dirname);
void LoadInferenceModel(const std::string& dirname,
const std::vector<std::string>& feed_var_names,
const std::vector<std::string>& fetch_var_names);
......
......@@ -15,6 +15,7 @@ import os
import cPickle as pickle
from paddle.v2.fluid.framework import Program, Parameter, default_main_program, Variable
from . import core
__all__ = [
'save_vars',
......@@ -191,6 +192,33 @@ def get_inference_program(target_vars, main_program=None):
return inference_program
def prepend_feed_ops(inference_program, feeded_var_names):
global_block = inference_program.global_block()
feed_var = global_block.create_var(
name='feed', type=core.VarDesc.VarType.FEED_MINIBATCH, persistable=True)
for i, name in enumerate(feeded_var_names):
out = global_block.var(name)
global_block.prepend_op(
type='feed',
inputs={'X': [feed_var]},
outputs={'Out': [out]},
attrs={'col': i})
def append_fetch_ops(inference_program, fetch_var_names):
global_block = inference_program.global_block()
fetch_var = global_block.create_var(
name='fetch', type=core.VarDesc.VarType.FETCH_LIST, persistable=True)
for i, name in enumerate(fetch_var_names):
global_block.append_op(
type='fetch',
inputs={'X': [name]},
outputs={'Out': [fetch_var]},
attrs={'col': i})
def save_inference_model(dirname,
feeded_var_names,
target_vars,
......@@ -241,6 +269,9 @@ def save_inference_model(dirname,
"fetch_var_names": fetch_var_names
}, f, -1)
prepend_feed_ops(inference_program, feeded_var_names)
append_fetch_ops(inference_program, fetch_var_names)
# Save only programDesc of inference_program in binary format
# in another file: __model__.dat
with open(model_file_name + ".dat", "wb") as fp:
......
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
新手
引导
客服 返回
顶部