From 8af285271fd3f94c5d23df9b20662ecd8e5d7f0a Mon Sep 17 00:00:00 2001 From: liuqi Date: Wed, 30 May 2018 14:26:10 +0800 Subject: [PATCH] Update docs for latest usage. --- .../create_a_model_deployment.rst | 39 ++-- docs/getting_started/how_to_build.rst | 30 +-- .../models/demo_app_models.yaml | 2 +- mace/benchmark/statistics.cc | 2 +- tools/bazel_adb_run.py | 9 +- tools/{mace_tools.py => converter.py} | 196 +++++++++++------ tools/sh_commands.py | 201 ++++++++---------- 7 files changed, 263 insertions(+), 216 deletions(-) rename tools/{mace_tools.py => converter.py} (87%) diff --git a/docs/getting_started/create_a_model_deployment.rst b/docs/getting_started/create_a_model_deployment.rst index d949c7b7..918c84a2 100644 --- a/docs/getting_started/create_a_model_deployment.rst +++ b/docs/getting_started/create_a_model_deployment.rst @@ -30,22 +30,31 @@ Configurations :header-rows: 1 :align: left - * - Configuration key - - Description + * - library_name + - library name * - target_abis - The target ABI to build, can be one or more of 'host', 'armeabi-v7a' or 'arm64-v8a' + * - target_socs + - build for specified socs if you just want use the model for that socs. * - embed_model_data - - Whether embedding model weights as the code, default to 1 + - Whether embedding model weights as the code, default to 0 + * - build_type + - model build type, can be ['proto', 'code']. 'proto' for converting model to ProtoBuf file and 'code' for converting model to c++ code. + * - model_name + - model name. should be unique if there are multiple models. + **LIMIT: if build_type is code, model_name will used in c++ code so that model_name must fulfill c++ name specification.** * - platform - - The source framework, tensorflow or caffe + - The source framework, one of [tensorflow, caffe] * - model_file_path - The path of the model file, can be local or remote - * - weight_file_path - - The path of the model weights file, used by Caffe model * - model_sha256_checksum - The SHA256 checksum of the model file + * - weight_file_path + - The path of the model weights file, used by Caffe model * - weight_sha256_checksum - The SHA256 checksum of the weight file, used by Caffe model + * - subgraphs + - subgraphs key. ** DO NOT EDIT ** * - input_tensors - The input tensor names (tensorflow), top name of inputs' layer (caffe). one or more strings * - output_tensors @@ -55,14 +64,16 @@ Configurations * - output_shapes - The shapes of the output tensors, in NHWC order * - runtime - - The running device, one of CPU, GPU or DSP + - The running device, one of [cpu, gpu, dsp, cpu_gpu]. cpu_gpu contains cpu and gpu model definition so you can run the model on both cpu and gpu. + * - data_type + - [optional] The data type used for specified runtime. [fp16_fp32, fp32_fp32] for gpu, default is fp16_fp32. [fp32] for cpu. [uint8] for dsp. * - limit_opencl_kernel_time - - Whether splitting the OpenCL kernel within 1 ms to keep UI responsiveness, default to 0 - * - dsp_mode - - Control the DSP precision and performance, default to 0 usually works for most cases + - [optional] Whether splitting the OpenCL kernel within 1 ms to keep UI responsiveness, default to 0 + * - nnlib_graph_mode + - [optional] Control the DSP precision and performance, default to 0 usually works for most cases * - obfuscate - - Whether to obfuscate the model operator name, default to 0 - * - fast_conv - - Whether to enable Winograd convolution, **will increase memory consumption** + - [optional] Whether to obfuscate the model operator name, default to 0 + * - winograd + - [optional] Whether to enable Winograd convolution, **will increase memory consumption** * - input_files - - Specify Numpy validation inputs. When not provided, [-1, 1] random values will be used + - [optional] Specify Numpy validation inputs. When not provided, [-1, 1] random values will be used diff --git a/docs/getting_started/how_to_build.rst b/docs/getting_started/how_to_build.rst index ea9da202..b9ff430a 100644 --- a/docs/getting_started/how_to_build.rst +++ b/docs/getting_started/how_to_build.rst @@ -166,11 +166,11 @@ Caffe目前只支持最新版本，旧版本请使用Caffe的工具进行升级 模型静态库的生成需要使用目标机型，\ ***并且要求必须在目标SOC的机型上编译生成静态库。*** -我们提供了\ ``mace_tools.py``\ 工具，可以将模型文件转换成静态库。\ ``tools/mace_tools.py``\ 使用步骤： +我们提供了\ ``converter.py``\ 工具，可以将模型文件转换成静态库。\ ``tools/converter.py``\ 使用步骤： -3.2 运行\ ``tools/mace_tools.py``\ 脚本 +3.2 运行\ ``tools/converter.py``\ 脚本 **Commands** @@ -181,8 +181,8 @@ Caffe目前只支持最新版本，旧版本请使用Caffe的工具进行升级 build模型静态库以及测试工具。 * *--config* (type=str, default="", required)：模型配置yaml文件路径. - * *--tuning* (optional)：是否为特定SOC调制GPU参数. - * *--enable_openmp* (optional)：是否启用openmp. + * *--tuning* (default=false, optional)：是否为特定SOC调制GPU参数. + * *--enable_openmp* (default=true, optional)：是否启用openmp. **run** @@ -192,10 +192,10 @@ Caffe目前只支持最新版本，旧版本请使用Caffe的工具进行升级 * *--config* (type=str, default="", required)：模型配置yaml文件路径. * *--round* (type=int, default=1, optional)：模型运行次数。 - * *--validate* (optional): 是否需要验证运行结果与框架运行结果是否一致。 + * *--validate* (default=false, optional): 是否需要验证运行结果与框架运行结果是否一致。 * *--caffe_env* (type=local/docker, default=docker, optional)：当vaildate时，可以选择指定caffe环境,local表示本地，docker表示使用docker容器. * *--restart_round* (type=int, default=1, optional)：模型重启次数。 - * *--check_gpu_out_of_memory* (optional): 是否需要检查gpu内存越界。 + * *--check_gpu_out_of_memory* (default=false, optional): 是否需要检查gpu内存越界。 * *--vlog_level* (type=int[0-5], default=0, optional)：详细日志级别. .. warning:: @@ -256,26 +256,26 @@ Caffe目前只支持最新版本，旧版本请使用Caffe的工具进行升级 .. code:: sh # print help message - python tools/mace_tools.py -h - python tools/mace_tools.py build -h - python tools/mace_tools.py run -h - python tools/mace_tools.py benchmark -h + python tools/converter.py -h + python tools/converter.py build -h + python tools/converter.py run -h + python tools/converter.py benchmark -h # 仅编译模型和生成静态库 - python tools/mace_tools.py build --config=models/config.yaml + python tools/converter.py build --config=models/config.yaml # 测试模型的运行时间 - python tools/mace_tools.py run --config=models/config.yaml --round=100 + python tools/converter.py run --config=models/config.yaml --round=100 # 对比编译好的模型在mace上与直接使用tensorflow或者caffe运行的结果，相似度使用`余弦距离表示` # 其中使用OpenCL设备，默认相似度大于等于`0.995`为通过；DSP设备下，相似度需要达到`0.930`。 - python tools/mace_tools.py run --config=models/config.yaml --validate + python tools/converter.py run --config=models/config.yaml --validate # 模型Benchmark：查看每个Op的运行时间 - python tools/mace_tools.py benchmark --config=models/config.yaml + python tools/converter.py benchmark --config=models/config.yaml # 查看模型运行时占用内存（如果有多个模型，可能需要注释掉一部分配置，只剩一个模型的配置） - python tools/mace_tools.py run --config=models/config.yaml --round=10000 & + python tools/converter.py run --config=models/config.yaml --round=10000 & adb shell dumpsys meminfo | grep mace_run sleep 10 kill %1 diff --git a/docs/getting_started/models/demo_app_models.yaml b/docs/getting_started/models/demo_app_models.yaml index bdd68edd..f78dc40a 100644 --- a/docs/getting_started/models/demo_app_models.yaml +++ b/docs/getting_started/models/demo_app_models.yaml @@ -7,7 +7,7 @@ target_socs: [msm8998] embed_model_data: 1 build_type: code # 模型build类型。code表示将模型转为代码，proto表示将模型转为protobuf文件 models: # 一个配置文件可以包含多个模型的配置信息，最终生成的库中包含多个模型 - first_net: # 模型的标签，在调度模型的时候，会用这个变量，必须唯一 + model_name: # 模型的标签，在调度模型的时候，会用这个变量，必须唯一 platform: tensorflow model_file_path: path/to/model64.pb # also support http:// and https:// model_sha256_checksum: 7f7462333406e7dea87222737590ebb7d94490194d2f21a7d72bafa87e64e9f9 diff --git a/mace/benchmark/statistics.cc b/mace/benchmark/statistics.cc index ddc1c058..bc68dd64 100644 --- a/mace/benchmark/statistics.cc +++ b/mace/benchmark/statistics.cc @@ -238,7 +238,7 @@ std::string OpStat::StatByNodeType() const { std::string OpStat::Summary() const { std::stringstream stream; if (!records_.empty()) { - stream << total_time_.ToString("Summary") << std::endl; + stream << total_time_.ToString("Summary of Ops' Stat") << std::endl; } stream << records_.size() << " ops total." << std::endl; diff --git a/tools/bazel_adb_run.py b/tools/bazel_adb_run.py index c67c2a85..40c4b5fb 100644 --- a/tools/bazel_adb_run.py +++ b/tools/bazel_adb_run.py @@ -136,11 +136,6 @@ def main(unused_args): sh_commands.gen_mace_version() sh_commands.gen_tuning_param_code([]) - strip = "always" - debug = False - if FLAGS.address_sanitizer: - strip = "never" - debug = True for target_abi in target_abis: sh_commands.bazel_build(target, abi=target_abi, enable_neon=FLAGS.enable_neon, @@ -158,10 +153,10 @@ def main(unused_args): host_bin_path, bin_name, args=FLAGS.args, - opencl_profiling=1, + opencl_profiling=True, vlog_level=0, device_bin_path="/data/local/tmp/mace", - out_of_range_check=1, + out_of_range_check=True, address_sanitizer=FLAGS.address_sanitizer) device_properties = sh_commands.adb_getprop_by_serialno( serialno) diff --git a/tools/mace_tools.py b/tools/converter.py similarity index 87% rename from tools/mace_tools.py rename to tools/converter.py index 7bafee33..58bd3a5a 100644 --- a/tools/mace_tools.py +++ b/tools/converter.py @@ -12,21 +12,17 @@ # See the License for the specific language governing permissions and # limitations under the License. -# python tools/mace_tools.py \ -# --config=tools/example.yaml \ -# --round=100 \ -# --mode=all - import argparse import filelock import hashlib import os +import re import sh import subprocess import sys import urllib import yaml -import re + from enum import Enum import sh_commands @@ -46,13 +42,23 @@ MODEL_OUTPUT_DIR_NAME = 'model' BUILD_TMP_DIR_NAME = '_tmp' BUILD_TMP_GENERAL_OUTPUT_DIR_NAME = 'general' OUTPUT_LIBRARY_DIR_NAME = 'library' +CL_BUILT_KERNEL_FILE_NAME = "mace_cl_compiled_program.bin" +CL_PLATFORM_INFO_FILE_NAME = "mace_cl_platform_info.txt" +CODEGEN_BASE_DIR = 'mace/codegen' +MODEL_CODEGEN_DIR = CODEGEN_BASE_DIR + '/models' +MACE_RUN_TARGET = "//mace/tools/validation:mace_run" ABITypeStrs = [ - "armeabi-v7a", - "arm64-v8a", - "host", + 'armeabi-v7a', + 'arm64-v8a', + 'host', ] -ABIType = Enum('ABIType', [(ele, ele) for ele in ABITypeStrs], type=str) + + +class ABIType(object): + armeabi_v7a = 'armeabi-v7a' + arm64_v8a = 'arm64-v8a' + host = 'host' PlatformTypeStrs = [ @@ -92,6 +98,13 @@ GPUDataTypeStrs = [ GPUDataType = Enum('GPUDataType', [(ele, ele) for ele in GPUDataTypeStrs], type=str) +DSPDataTypeStrs = [ + "uint8", +] + +DSPDataType = Enum('DSPDataType', [(ele, ele) for ele in DSPDataTypeStrs], + type=str) + class DefaultValues(object): omp_num_threads = -1, @@ -129,6 +142,8 @@ class YAMLKeyword(object): class ModuleName(object): YAML_CONFIG = 'YAML CONFIG' MODEL_CONVERTER = 'Model Converter' + RUN = 'RUN' + BENCHMARK = 'Benchmark' CPP_KEYWORDS = [ @@ -171,11 +186,13 @@ def parse_device_type(runtime): def get_hexagon_mode(configs): runtime_list = [] - for model_name in configs["models"]: - model_runtime = configs["models"][model_name].get("runtime", "") + for model_name in configs[YAMLKeyword.models]: + model_runtime =\ + configs[YAMLKeyword.models][model_name].get( + YAMLKeyword.runtime, "") runtime_list.append(model_runtime.lower()) - if "dsp" in runtime_list: + if RuntimeType.dsp in runtime_list: return True return False @@ -200,7 +217,7 @@ def format_model_config(config_file_path): library_name = configs.get(YAMLKeyword.library_name, "") mace_check(len(library_name) > 0, - ModuleName.YAML_CONFIG, "library name shuold not be empty") + ModuleName.YAML_CONFIG, "library name should not be empty") target_abis = configs.get(YAMLKeyword.target_abis, []) mace_check((isinstance(target_abis, list) and len(target_abis) > 0), @@ -216,7 +233,8 @@ def format_model_config(config_file_path): elif not isinstance(target_socs, list): configs[YAMLKeyword.target_socs] = [target_socs] - if ABIType.host not in target_abis: + if ABIType.armeabi_v7a in target_abis \ + or ABIType.arm64_v8a in target_abis: available_socs = sh_commands.adb_get_all_socs() if YAMLKeyword.target_socs in configs: target_socs = set(configs[YAMLKeyword.target_socs]) @@ -261,7 +279,7 @@ def format_model_config(config_file_path): mace_check((model_name[0] == '_' or model_name[0].isalpha()) and bool(model_name_reg.match(model_name)), ModuleName.YAML_CONFIG, - "model name shuold Meet the c++ naming convention" + "model name should Meet the c++ naming convention" " which start with '_' or alpha" " and only contain alpha, number and '_'") @@ -318,6 +336,15 @@ def format_model_config(config_file_path): else: model_config[YAMLKeyword.data_type] =\ GPUDataType.fp16_fp32.value + elif runtime == RuntimeType.dsp: + if len(data_type) > 0: + mace_check(data_type in DSPDataTypeStrs, + ModuleName.YAML_CONFIG, + "'data_type' must be in " + str(DSPDataTypeStrs) + + " for dsp runtime") + else: + model_config[YAMLKeyword.data_type] = \ + DSPDataType.uint8.value subgraphs = model_config.get(YAMLKeyword.subgraphs, "") mace_check(len(subgraphs) > 0, ModuleName.YAML_CONFIG, @@ -342,15 +369,17 @@ def format_model_config(config_file_path): if value == "": model_config[key] = 0 - validation_inputs_data = model_config.get("validation_inputs_data", - []) - model_config["validation_inputs_data"] = validation_inputs_data + validation_inputs_data = model_config.get( + YAMLKeyword.validation_inputs_data, []) if not isinstance(validation_inputs_data, list): - model_config["validation_inputs_data"] = [ + model_config[YAMLKeyword.validation_inputs_data] = [ validation_inputs_data] + else: + model_config[YAMLKeyword.validation_inputs_data] = \ + validation_inputs_data - weight_file_path = model_config.get("weight_file_path", "") - model_config["weight_file_path"] = weight_file_path + weight_file_path = model_config.get(YAMLKeyword.weight_file_path, "") + model_config[YAMLKeyword.weight_file_path] = weight_file_path return configs @@ -359,9 +388,9 @@ def get_build_binary_dir(library_name, target_abi, target_soc, serial_num): if not target_soc or not serial_num: binary_path_digest = md5sum(target_abi) + binary_path_digest = "%s_%s" % (target_abi, binary_path_digest) else: - device_name = sh_commands.adb_get_device_name_by_serialno(serial_num)\ - .replace(' ', '') + device_name = sh_commands.adb_get_device_name_by_serialno(serial_num) binary_path_digest = md5sum(target_abi + target_soc + serial_num) binary_path_digest = "%s_%s_%s" % \ (device_name, target_soc, binary_path_digest) @@ -386,7 +415,7 @@ def get_build_model_dirs(library_name, model_name, target_abi, target_soc, device_name = \ sh_commands.adb_get_device_name_by_serialno(serial_num) model_output_dir = "%s/%s_%s/%s" % ( - model_output_base_dir, device_name.replace(' ', ''), + model_output_base_dir, device_name, target_soc, target_abi) mace_model_dir = \ @@ -401,21 +430,16 @@ def get_build_model_dirs(library_name, model_name, target_abi, target_soc, def pull_opencl_binary_and_tuning_param(target_abi, serialno, model_output_dirs): - cl_built_kernel_file_name = "mace_cl_compiled_program.bin" - cl_platform_info_file_name = "mace_cl_platform_info.txt" sh_commands.pull_binaries(target_abi, serialno, model_output_dirs, - cl_built_kernel_file_name, - cl_platform_info_file_name) + CL_BUILT_KERNEL_FILE_NAME, + CL_PLATFORM_INFO_FILE_NAME) def gen_opencl_and_tuning_code(model_output_dirs): - cl_built_kernel_file_name = "mace_cl_compiled_program.bin" - cl_platform_info_file_name = "mace_cl_platform_info.txt" - # generate opencl binary code sh_commands.gen_opencl_binary_code(model_output_dirs, - cl_built_kernel_file_name, - cl_platform_info_file_name) + CL_BUILT_KERNEL_FILE_NAME, + CL_PLATFORM_INFO_FILE_NAME) sh_commands.gen_tuning_param_code(model_output_dirs) @@ -475,8 +499,9 @@ def convert_model(configs): library_name = configs[YAMLKeyword.library_name] if not os.path.exists(BUILD_OUTPUT_DIR): os.makedirs(BUILD_OUTPUT_DIR) - elif not os.path.exists(os.path.join(BUILD_OUTPUT_DIR, library_name)): - os.makedirs(os.path.join(BUILD_OUTPUT_DIR, library_name)) + elif os.path.exists(os.path.join(BUILD_OUTPUT_DIR, library_name)): + sh.rm("-rf", os.path.join(BUILD_OUTPUT_DIR, library_name)) + os.makedirs(os.path.join(BUILD_OUTPUT_DIR, library_name)) model_output_dir = \ '%s/%s/%s' % (BUILD_OUTPUT_DIR, library_name, MODEL_OUTPUT_DIR_NAME) @@ -527,12 +552,10 @@ def convert_model(configs): "weight file sha256checksum not match") data_type = model_config[YAMLKeyword.data_type] - if ABIType.host.value in configs[YAMLKeyword.target_abis]: - data_type = CPUDataType.fp32.value # TODO(liuqi): support multiple subgraphs subgraphs = model_config[YAMLKeyword.subgraphs] - model_codegen_dir = "mace/codegen/models/%s" % model_name + model_codegen_dir = "%s/%s" % (MODEL_CODEGEN_DIR, model_name) sh_commands.gen_model_code( model_codegen_dir, model_config[YAMLKeyword.platform], @@ -561,14 +584,13 @@ def convert_model(configs): output_dir=model_output_dir ) - MaceLogger.header( + MaceLogger.summary( StringFormatter.block("Model %s converted" % model_name)) def build_specific_lib(target_abi, target_soc, serial_num, configs, tuning, enable_openmp, address_sanitizer): - mace_run_target = "//mace/tools/validation:mace_run" library_name = configs[YAMLKeyword.library_name] build_type = configs[YAMLKeyword.build_type] embed_model_data = configs[YAMLKeyword.embed_model_data] @@ -583,7 +605,7 @@ def build_specific_lib(target_abi, target_soc, serial_num, gen_opencl_and_tuning_code([]) sh_commands.bazel_build( - mace_run_target, + MACE_RUN_TARGET, abi=target_abi, hexagon_mode=hexagon_mode, enable_openmp=enable_openmp, @@ -608,7 +630,7 @@ def build_specific_lib(target_abi, target_soc, serial_num, os.makedirs(model_output_dir) # build for specified soc - if not address_sanitizer and target_abi != ABIType.host \ + if not address_sanitizer and tuning and target_abi != ABIType.host \ and target_soc is not None and \ model_runtime in [RuntimeType.gpu, RuntimeType.cpu_gpu]: sh_commands.clear_phone_data_dir(serial_num, PHONE_DATA_DIR) @@ -653,7 +675,7 @@ def build_specific_lib(target_abi, target_soc, serial_num, if binary_changed: gen_opencl_and_tuning_code(model_output_dirs) sh_commands.bazel_build( - mace_run_target, + MACE_RUN_TARGET, abi=target_abi, hexagon_mode=hexagon_mode, enable_openmp=enable_openmp, @@ -671,6 +693,7 @@ def build_specific_lib(target_abi, target_soc, serial_num, # generate library sh_commands.merge_libs(target_soc, + serial_num, target_abi, library_name, BUILD_OUTPUT_DIR, @@ -705,17 +728,18 @@ def generate_library(configs, tuning, enable_openmp, address_sanitizer): target_socs = configs[YAMLKeyword.target_socs] for target_abi in configs[YAMLKeyword.target_abis]: - if not target_socs or target_abi == ABIType.host.value: + if not target_socs or target_abi == ABIType.host: build_specific_lib(target_abi, None, None, configs, tuning, enable_openmp, address_sanitizer) else: for target_soc in target_socs: - serial_num = sh_commands.get_target_soc_serial_number( - target_soc) - with sh_commands.device_lock(serial_num): - build_specific_lib(target_abi, target_soc, serial_num, - configs, tuning, enable_openmp, - address_sanitizer) + serial_nums = \ + sh_commands.get_target_socs_serialnos([target_soc]) + for serial_num in serial_nums: + with sh_commands.device_lock(serial_num): + build_specific_lib(target_abi, target_soc, serial_num, + configs, tuning, enable_openmp, + address_sanitizer) # package library sh_commands.packaging_lib(BUILD_OUTPUT_DIR, @@ -804,8 +828,19 @@ def run_specific_target(flags, configs, target_abi, else: build_tmp_binary_dir = get_build_binary_dir(library_name, target_abi, target_soc, serial_num) + mace_check(os.path.exists(build_tmp_binary_dir), + ModuleName.RUN, + 'You should build before run.') for model_name in configs[YAMLKeyword.models]: + if target_abi == ABIType.host: + device_name = ABIType.host + else: + device_name =\ + sh_commands.adb_get_device_name_by_serialno(serial_num) + MaceLogger.header( + StringFormatter.block( + "Run model %s on %s" % (model_name, device_name))) model_config = configs[YAMLKeyword.models][model_name] model_runtime = model_config[YAMLKeyword.runtime] subgraphs = model_config[YAMLKeyword.subgraphs] @@ -820,6 +855,10 @@ def run_specific_target(flags, configs, target_abi, get_build_model_dirs(library_name, model_name, target_abi, target_soc, serial_num, model_config[YAMLKeyword.model_file_path]) + mace_check(os.path.exists(model_output_dir) + and os.path.exists(mace_model_dir), + ModuleName.RUN, + 'You should build before run.') if target_abi != ABIType.host: sh_commands.clear_phone_data_dir(serial_num, PHONE_DATA_DIR) @@ -869,9 +908,9 @@ def run_specific_target(flags, configs, target_abi, ) if flags.validate: model_file_path, weight_file_path = get_model_files_path( - model_config["model_file_path"], + model_config[YAMLKeyword.model_file_path], model_output_base_dir, - model_config["weight_file_path"]) + model_config[YAMLKeyword.weight_file_path]) sh_commands.validate_model( abi=target_abi, @@ -899,20 +938,21 @@ def run_mace(flags): target_socs = configs[YAMLKeyword.target_socs] if not target_socs: target_socs = sh_commands.adb_get_all_socs() - if ABIType.host not in configs[YAMLKeyword.target_abis] \ - and not target_socs: - MaceLogger.warning('There is no device plugin the computer.') for target_abi in configs[YAMLKeyword.target_abis]: if target_abi == ABIType.host: run_specific_target(flags, configs, target_abi, None, None) else: for target_soc in target_socs: - serial_num = sh_commands.get_target_soc_serial_number( - target_soc) - with sh_commands.device_lock(serial_num): - run_specific_target(flags, configs, target_abi, - target_soc, serial_num) + serial_nums = \ + sh_commands.get_target_socs_serialnos([target_soc]) + mace_check(serial_nums, + ModuleName.RUN, + 'There is no device with soc: ' + target_soc) + for serial_num in serial_nums: + with sh_commands.device_lock(serial_num): + run_specific_target(flags, configs, target_abi, + target_soc, serial_num) ################################ @@ -928,8 +968,19 @@ def bm_specific_target(flags, configs, target_abi, target_soc, serial_num): else: build_tmp_binary_dir = get_build_binary_dir(library_name, target_abi, target_soc, serial_num) + mace_check(os.path.exists(build_tmp_binary_dir), + ModuleName.BENCHMARK, + 'You should build before benchmark.') for model_name in configs[YAMLKeyword.models]: + if target_abi == ABIType.host: + device_name = ABIType.host + else: + device_name = \ + sh_commands.adb_get_device_name_by_serialno(serial_num) + MaceLogger.header( + StringFormatter.block( + "Benchmark model %s on %s" % (model_name, device_name))) model_config = configs[YAMLKeyword.models][model_name] model_runtime = model_config[YAMLKeyword.runtime] subgraphs = model_config[YAMLKeyword.subgraphs] @@ -944,6 +995,10 @@ def bm_specific_target(flags, configs, target_abi, target_soc, serial_num): get_build_model_dirs(library_name, model_name, target_abi, target_soc, serial_num, model_config[YAMLKeyword.model_file_path]) + mace_check(os.path.exists(model_output_dir) + and os.path.exists(mace_model_dir), + ModuleName.BENCHMARK, + 'You should build before benchmark.') if target_abi != ABIType.host: sh_commands.clear_phone_data_dir(serial_num, PHONE_DATA_DIR) @@ -990,20 +1045,21 @@ def benchmark_model(flags): target_socs = configs[YAMLKeyword.target_socs] if not target_socs: target_socs = sh_commands.adb_get_all_socs() - if ABIType.host.value not in configs[YAMLKeyword.target_abis] \ - and not target_socs: - MaceLogger.warning('There is no device plugin the computer.') for target_abi in configs[YAMLKeyword.target_abis]: - if target_abi == ABIType.host.value: + if target_abi == ABIType.host: bm_specific_target(flags, configs, target_abi, None, None) else: for target_soc in target_socs: - serial_num = sh_commands.get_target_soc_serial_number( - target_soc) - with sh_commands.device_lock(serial_num): - bm_specific_target(flags, configs, target_abi, - target_soc, serial_num) + serial_nums = \ + sh_commands.get_target_socs_serialnos([target_soc]) + mace_check(serial_nums, + ModuleName.BENCHMARK, + 'There is no device with soc: ' + target_soc) + for serial_num in serial_nums: + with sh_commands.device_lock(serial_num): + bm_specific_target(flags, configs, target_abi, + target_soc, serial_num) ################################ diff --git a/tools/sh_commands.py b/tools/sh_commands.py index 81f69398..28bcaca0 100644 --- a/tools/sh_commands.py +++ b/tools/sh_commands.py @@ -165,7 +165,7 @@ def adb_getprop_by_serialno(serialno): def adb_get_device_name_by_serialno(serialno): props = adb_getprop_by_serialno(serialno) - return props.get("ro.product.model", "") + return props.get("ro.product.model", "").replace(' ', '') def adb_supported_abis(serialno): @@ -201,10 +201,10 @@ def adb_run(abi, host_bin_path, bin_name, args="", - opencl_profiling=1, + opencl_profiling=True, vlog_level=0, device_bin_path="/data/local/tmp/mace", - out_of_range_check=1, + out_of_range_check=True, address_sanitizer=False): host_bin_full_path = "%s/%s" % (host_bin_path, bin_name) device_bin_full_path = "%s/%s" % (device_bin_path, bin_name) @@ -225,11 +225,13 @@ def adb_run(abi, adb_push(find_asan_rt_library(abi), device_bin_path, serialno) ld_preload = "LD_PRELOAD=%s/%s" % (device_bin_path, asan_rt_library_names(abi)), + opencl_profiling = 1 if opencl_profiling else 0 + out_of_range_check = 1 if out_of_range_check else 0 print("Run %s" % device_bin_full_path) stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.adb( + sh.adb( "-s", serialno, "shell", @@ -239,9 +241,7 @@ def adb_run(abi, "MACE_CPP_MIN_VLOG_LEVEL=%d" % vlog_level, "%s %s" % (device_bin_full_path, args), _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + _fg=True) return "".join(stdout_buff) @@ -309,12 +309,10 @@ def bazel_build(target, bazel_args += ("--config", "asan") else: bazel_args += ("--config", "optimization") - p = sh.bazel( + sh.bazel( _out=process_output, - _bg=True, - _err_to_out=True, + _fg=True, *bazel_args) - p.wait() print("Build done!\n") return "".join(stdout_buff) @@ -322,13 +320,11 @@ def bazel_build(target, def bazel_build_common(target, build_args=""): stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.bazel( + sh.bazel( "build", target + build_args, _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + _fg=True) return "".join(stdout_buff) @@ -462,30 +458,28 @@ def gen_model_code(model_codegen_dir, stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.python("bazel-bin/mace/python/tools/converter", - "-u", - "--platform=%s" % platform, - "--model_file=%s" % model_file_path, - "--weight_file=%s" % weight_file_path, - "--model_checksum=%s" % model_sha256_checksum, - "--weight_checksum=%s" % weight_sha256_checksum, - "--input_node=%s" % input_nodes, - "--output_node=%s" % output_nodes, - "--runtime=%s" % runtime, - "--template=%s" % "mace/python/tools", - "--model_tag=%s" % model_tag, - "--input_shape=%s" % input_shapes, - "--dsp_mode=%s" % dsp_mode, - "--embed_model_data=%s" % embed_model_data, - "--winograd=%s" % fast_conv, - "--obfuscate=%s" % obfuscate, - "--output_dir=%s" % model_codegen_dir, - "--model_build_type=%s" % model_build_type, - "--data_type=%s" % data_type, - _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + sh.python("bazel-bin/mace/python/tools/converter", + "-u", + "--platform=%s" % platform, + "--model_file=%s" % model_file_path, + "--weight_file=%s" % weight_file_path, + "--model_checksum=%s" % model_sha256_checksum, + "--weight_checksum=%s" % weight_sha256_checksum, + "--input_node=%s" % input_nodes, + "--output_node=%s" % output_nodes, + "--runtime=%s" % runtime, + "--template=%s" % "mace/python/tools", + "--model_tag=%s" % model_tag, + "--input_shape=%s" % input_shapes, + "--dsp_mode=%s" % dsp_mode, + "--embed_model_data=%s" % embed_model_data, + "--winograd=%s" % fast_conv, + "--obfuscate=%s" % obfuscate, + "--output_dir=%s" % model_codegen_dir, + "--model_build_type=%s" % model_build_type, + "--data_type=%s" % data_type, + _out=process_output, + _fg=True) def gen_random_input(model_output_dir, @@ -692,15 +686,13 @@ def tuning_run(abi, "--model_file=%s" % mace_model_phone_path, ]) adb_cmd = ' '.join(adb_cmd) - p = sh.adb( + sh.adb( "-s", serialno, "shell", adb_cmd, _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + _fg=True) print("Running finished!\n") return "".join(stdout_buff) @@ -802,26 +794,24 @@ def validate_model(abi, stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.docker( - "exec", - container_name, - "python", - "-u", - "/mace/validate.py", - "--platform=caffe", - "--model_file=/mace/%s" % model_file_name, - "--weight_file=/mace/%s" % weight_file_name, - "--input_file=/mace/%s" % input_file_name, - "--mace_out_file=/mace/%s" % output_file_name, - "--device_type=%s" % device_type, - "--input_node=%s" % ",".join(input_nodes), - "--output_node=%s" % ",".join(output_nodes), - "--input_shape=%s" % ":".join(input_shapes), - "--output_shape=%s" % ":".join(output_shapes), - _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + sh.docker( + "exec", + container_name, + "python", + "-u", + "/mace/validate.py", + "--platform=caffe", + "--model_file=/mace/%s" % model_file_name, + "--weight_file=/mace/%s" % weight_file_name, + "--input_file=/mace/%s" % input_file_name, + "--mace_out_file=/mace/%s" % output_file_name, + "--device_type=%s" % device_type, + "--input_node=%s" % ",".join(input_nodes), + "--output_node=%s" % ",".join(output_nodes), + "--input_shape=%s" % ":".join(input_shapes), + "--output_shape=%s" % ":".join(output_shapes), + _out=process_output, + _fg=True) print("Validation done!\n") @@ -843,6 +833,7 @@ def build_host_libraries(model_build_type, abi): def merge_libs(target_soc, + serial_num, abi, project_name, build_output_dir, @@ -911,8 +902,10 @@ def merge_libs(target_soc, mri_stream += "create %s/libmace_%s.a\n" % \ (model_bin_dir, project_name) else: - mri_stream += "create %s/libmace_%s.%s.a\n" % \ - (model_bin_dir, project_name, target_soc) + device_name = adb_get_device_name_by_serialno(serial_num) + mri_stream += "create %s/libmace_%s.%s.%s.a\n" % \ + (model_bin_dir, project_name, + device_name, target_soc) if model_build_type == BuildType.code: mri_stream += ( "addlib " @@ -969,16 +962,14 @@ def packaging_lib(libmace_output_dir, project_name): tar_package_path)) stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.tar( - "cvzf", - "%s" % tar_package_path, - glob.glob("%s/*" % project_dir), - "--exclude", - "%s/_tmp" % project_dir, - _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + sh.tar( + "cvzf", + "%s" % tar_package_path, + glob.glob("%s/*" % project_dir), + "--exclude", + "%s/_tmp" % project_dir, + _out=process_output, + _fg=True) print("Packaging Done!\n") @@ -1068,7 +1059,7 @@ def benchmark_model(abi, adb_push("%s/benchmark_model" % benchmark_binary_dir, phone_data_dir, serialno) - p = sh.adb( + sh.adb( "-s", serialno, "shell", @@ -1093,9 +1084,7 @@ def benchmark_model(abi, "--gpu_priority_hint=%s" % gpu_priority_hint, "--model_file=%s" % mace_model_phone_path, _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + _fg=True) print("Benchmark done!\n") return "".join(stdout_buff) @@ -1134,7 +1123,7 @@ def build_run_throughput_test(abi, sh.cp("-f", merged_lib_file, "mace/benchmark/libmace_merged.a") stdout_buff = [] process_output = make_output_processor(stdout_buff) - p = sh.bazel( + sh.bazel( "build", "-c", "opt", @@ -1155,9 +1144,7 @@ def build_run_throughput_test(abi, "openmp=true", model_tag_build_flag, _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + _fg=True) sh.rm("mace/benchmark/libmace_merged.a") sh.adb("-s", @@ -1187,31 +1174,29 @@ def build_run_throughput_test(abi, phone_data_dir, serialno) - p = sh.adb( - "-s", - serialno, - "shell", - "LD_LIBRARY_PATH=%s" % phone_data_dir, - "MACE_CPP_MIN_VLOG_LEVEL=%s" % vlog_level, - "MACE_RUN_PARAMETER_PATH=%s/mace_run.config" % - phone_data_dir, - "%s/model_throughput_test" % phone_data_dir, - "--input_node=%s" % ",".join(input_nodes), - "--output_node=%s" % ",".join(output_nodes), - "--input_shape=%s" % ":".join(input_shapes), - "--output_shape=%s" % ":".join(output_shapes), - "--input_file=%s/%s" % (phone_data_dir, input_file_name), - "--cpu_model_data_file=%s/%s.data" % (phone_data_dir, - cpu_model_tag), - "--gpu_model_data_file=%s/%s.data" % (phone_data_dir, - gpu_model_tag), - "--dsp_model_data_file=%s/%s.data" % (phone_data_dir, - dsp_model_tag), - "--run_seconds=%s" % run_seconds, - _out=process_output, - _bg=True, - _err_to_out=True) - p.wait() + sh.adb( + "-s", + serialno, + "shell", + "LD_LIBRARY_PATH=%s" % phone_data_dir, + "MACE_CPP_MIN_VLOG_LEVEL=%s" % vlog_level, + "MACE_RUN_PARAMETER_PATH=%s/mace_run.config" % + phone_data_dir, + "%s/model_throughput_test" % phone_data_dir, + "--input_node=%s" % ",".join(input_nodes), + "--output_node=%s" % ",".join(output_nodes), + "--input_shape=%s" % ":".join(input_shapes), + "--output_shape=%s" % ":".join(output_shapes), + "--input_file=%s/%s" % (phone_data_dir, input_file_name), + "--cpu_model_data_file=%s/%s.data" % (phone_data_dir, + cpu_model_tag), + "--gpu_model_data_file=%s/%s.data" % (phone_data_dir, + gpu_model_tag), + "--dsp_model_data_file=%s/%s.data" % (phone_data_dir, + dsp_model_tag), + "--run_seconds=%s" % run_seconds, + _out=process_output, + _fg=True) print("throughput_test done!\n") -- GitLab