From ac83a2bffa833e3e9d9038b4c71544f571d19045 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Wed, 3 Nov 2021 20:32:23 +0800 Subject: [PATCH 01/18] Complete file move --- nn_meter/__init__.py | 2 +- nn_meter/dataset/bench_dataset.py | 2 +- .../__init__.py | 0 .../frozenpb_converter/__init__.py | 0 .../frozenpb_converter/frozenpb_converter.py | 0 .../frozenpb_converter/frozenpb_parser.py | 0 .../frozenpb_converter/protobuf_helper.py | 0 .../frozenpb_converter/shape_fetcher.py | 0 .../frozenpb_converter/shape_inference.py | 0 .../onnx_converter/__init__.py | 0 .../onnx_converter/constants.py | 0 .../onnx_converter/converter.py | 0 .../onnx_converter/utils.py | 0 .../torch_converter/__init__.py | 0 .../torch_converter/converter.py | 2 +- .../torch_converter/opset_map.py | 0 .../{ir_converters => ir_converter}/utils.py | 0 .../__init__.py | 0 .../detection/__init__.py | 0 .../detection/detector.py | 8 +- .../fusionlib/__init__.py | 0 .../fusionlib/add-relu_fusionunit.json | 0 .../fusionlib/bn-relu_fusionunit.json | 0 .../fusionlib/channelshuffle_fusionunit.json | 0 .../fusionlib/conv-bn-relu_fusionunit.json | 0 .../fusionlib/conv-bn_fusionunit.json | 0 .../fusionlib/dwconv-bn-relu_fusionunit.json | 0 .../fusionlib/elewise_fusionunit.json | 0 .../fusionlib/gap_fusionunit.json | 0 .../fusionlib/hswish_fusionunit.json | 0 .../fusionlib/se_fusionunit.json | 0 .../fusionlib/utils.py | 2 +- .../rulelib/__init__.py | 0 .../rulelib/rule_reader.py | 2 +- .../rulelib/rule_splitter.py | 4 +- .../utils/__init__.py | 0 .../utils/constants.py | 0 .../utils/fusion_aware_graph.py | 0 .../utils/ir_tools.py | 0 .../utils/match_helper.py | 0 .../utils/union_find.py | 0 .../{prediction => predictor}/__init__.py | 0 .../nn_meter_predictor.py} | 69 ++-------------- .../predictors/__init__.py | 0 .../predictors/extract_feature.py | 0 .../predictors/kernel_predictor.py | 0 .../predictors/predict_by_kernel.py | 0 .../predictors/utils.py | 0 .../load_predictors.py => predictor/utils.py} | 0 nn_meter/utils/__init__.py | 6 ++ nn_meter/utils/config_manager.py | 69 ++++++++++++++++ nn_meter/utils/import_package.py | 78 +++++++++++++++++++ nn_meter/utils/utils.py | 73 ----------------- setup.py | 2 +- 54 files changed, 172 insertions(+), 147 deletions(-) rename nn_meter/{ir_converters => ir_converter}/__init__.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/__init__.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/frozenpb_converter.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/frozenpb_parser.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/protobuf_helper.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/shape_fetcher.py (100%) rename nn_meter/{ir_converters => ir_converter}/frozenpb_converter/shape_inference.py (100%) rename nn_meter/{ir_converters => ir_converter}/onnx_converter/__init__.py (100%) rename nn_meter/{ir_converters => ir_converter}/onnx_converter/constants.py (100%) rename nn_meter/{ir_converters => ir_converter}/onnx_converter/converter.py (100%) rename nn_meter/{ir_converters => ir_converter}/onnx_converter/utils.py (100%) rename nn_meter/{ir_converters => ir_converter}/torch_converter/__init__.py (100%) rename nn_meter/{ir_converters => ir_converter}/torch_converter/converter.py (98%) rename nn_meter/{ir_converters => ir_converter}/torch_converter/opset_map.py (100%) rename nn_meter/{ir_converters => ir_converter}/utils.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/__init__.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/detection/__init__.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/detection/detector.py (93%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/__init__.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/add-relu_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/bn-relu_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/channelshuffle_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/conv-bn-relu_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/conv-bn_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/dwconv-bn-relu_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/elewise_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/gap_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/hswish_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/se_fusionunit.json (100%) rename nn_meter/{kerneldetection => kernel_detector}/fusionlib/utils.py (88%) rename nn_meter/{kerneldetection => kernel_detector}/rulelib/__init__.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/rulelib/rule_reader.py (96%) rename nn_meter/{kerneldetection => kernel_detector}/rulelib/rule_splitter.py (95%) rename nn_meter/{kerneldetection => kernel_detector}/utils/__init__.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/utils/constants.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/utils/fusion_aware_graph.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/utils/ir_tools.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/utils/match_helper.py (100%) rename nn_meter/{kerneldetection => kernel_detector}/utils/union_find.py (100%) rename nn_meter/{prediction => predictor}/__init__.py (100%) rename nn_meter/{nn_meter.py => predictor/nn_meter_predictor.py} (68%) rename nn_meter/{prediction => predictor}/predictors/__init__.py (100%) rename nn_meter/{prediction => predictor}/predictors/extract_feature.py (100%) rename nn_meter/{prediction => predictor}/predictors/kernel_predictor.py (100%) rename nn_meter/{prediction => predictor}/predictors/predict_by_kernel.py (100%) rename nn_meter/{prediction => predictor}/predictors/utils.py (100%) rename nn_meter/{prediction/load_predictors.py => predictor/utils.py} (100%) create mode 100644 nn_meter/utils/config_manager.py create mode 100644 nn_meter/utils/import_package.py diff --git a/nn_meter/__init__.py b/nn_meter/__init__.py index da6b1d6a..2efbcef2 100644 --- a/nn_meter/__init__.py +++ b/nn_meter/__init__.py @@ -17,7 +17,7 @@ change_user_data_folder ) from .utils.utils import download_from_url -from .prediction import latency_metrics +from .predictor import latency_metrics from .dataset import bench_dataset # TODO: add GNNDataloader and GNNDataset here @wenxuan import logging from functools import partial, partialmethod diff --git a/nn_meter/dataset/bench_dataset.py b/nn_meter/dataset/bench_dataset.py index 1c034b4e..7e2b2249 100644 --- a/nn_meter/dataset/bench_dataset.py +++ b/nn_meter/dataset/bench_dataset.py @@ -1,7 +1,7 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. import os, sys -from nn_meter.prediction import latency_metrics +from nn_meter.predictor import latency_metrics from glob import glob from nn_meter.nn_meter import list_latency_predictors, load_latency_predictor, get_user_data_folder diff --git a/nn_meter/ir_converters/__init__.py b/nn_meter/ir_converter/__init__.py similarity index 100% rename from nn_meter/ir_converters/__init__.py rename to nn_meter/ir_converter/__init__.py diff --git a/nn_meter/ir_converters/frozenpb_converter/__init__.py b/nn_meter/ir_converter/frozenpb_converter/__init__.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/__init__.py rename to nn_meter/ir_converter/frozenpb_converter/__init__.py diff --git a/nn_meter/ir_converters/frozenpb_converter/frozenpb_converter.py b/nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/frozenpb_converter.py rename to nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py diff --git a/nn_meter/ir_converters/frozenpb_converter/frozenpb_parser.py b/nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/frozenpb_parser.py rename to nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py diff --git a/nn_meter/ir_converters/frozenpb_converter/protobuf_helper.py b/nn_meter/ir_converter/frozenpb_converter/protobuf_helper.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/protobuf_helper.py rename to nn_meter/ir_converter/frozenpb_converter/protobuf_helper.py diff --git a/nn_meter/ir_converters/frozenpb_converter/shape_fetcher.py b/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/shape_fetcher.py rename to nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py diff --git a/nn_meter/ir_converters/frozenpb_converter/shape_inference.py b/nn_meter/ir_converter/frozenpb_converter/shape_inference.py similarity index 100% rename from nn_meter/ir_converters/frozenpb_converter/shape_inference.py rename to nn_meter/ir_converter/frozenpb_converter/shape_inference.py diff --git a/nn_meter/ir_converters/onnx_converter/__init__.py b/nn_meter/ir_converter/onnx_converter/__init__.py similarity index 100% rename from nn_meter/ir_converters/onnx_converter/__init__.py rename to nn_meter/ir_converter/onnx_converter/__init__.py diff --git a/nn_meter/ir_converters/onnx_converter/constants.py b/nn_meter/ir_converter/onnx_converter/constants.py similarity index 100% rename from nn_meter/ir_converters/onnx_converter/constants.py rename to nn_meter/ir_converter/onnx_converter/constants.py diff --git a/nn_meter/ir_converters/onnx_converter/converter.py b/nn_meter/ir_converter/onnx_converter/converter.py similarity index 100% rename from nn_meter/ir_converters/onnx_converter/converter.py rename to nn_meter/ir_converter/onnx_converter/converter.py diff --git a/nn_meter/ir_converters/onnx_converter/utils.py b/nn_meter/ir_converter/onnx_converter/utils.py similarity index 100% rename from nn_meter/ir_converters/onnx_converter/utils.py rename to nn_meter/ir_converter/onnx_converter/utils.py diff --git a/nn_meter/ir_converters/torch_converter/__init__.py b/nn_meter/ir_converter/torch_converter/__init__.py similarity index 100% rename from nn_meter/ir_converters/torch_converter/__init__.py rename to nn_meter/ir_converter/torch_converter/__init__.py diff --git a/nn_meter/ir_converters/torch_converter/converter.py b/nn_meter/ir_converter/torch_converter/converter.py similarity index 98% rename from nn_meter/ir_converters/torch_converter/converter.py rename to nn_meter/ir_converter/torch_converter/converter.py index 451e4a67..1af2f43e 100644 --- a/nn_meter/ir_converters/torch_converter/converter.py +++ b/nn_meter/ir_converter/torch_converter/converter.py @@ -2,7 +2,7 @@ # Licensed under the MIT license. from nn_meter.utils.utils import try_import_onnx, try_import_torch, try_import_onnxsim, try_import_nni import tempfile -from nn_meter.ir_converters.onnx_converter import OnnxConverter +from nn_meter.ir_converter.onnx_converter import OnnxConverter from .opset_map import nni_attr_map, nni_type_map diff --git a/nn_meter/ir_converters/torch_converter/opset_map.py b/nn_meter/ir_converter/torch_converter/opset_map.py similarity index 100% rename from nn_meter/ir_converters/torch_converter/opset_map.py rename to nn_meter/ir_converter/torch_converter/opset_map.py diff --git a/nn_meter/ir_converters/utils.py b/nn_meter/ir_converter/utils.py similarity index 100% rename from nn_meter/ir_converters/utils.py rename to nn_meter/ir_converter/utils.py diff --git a/nn_meter/kerneldetection/__init__.py b/nn_meter/kernel_detector/__init__.py similarity index 100% rename from nn_meter/kerneldetection/__init__.py rename to nn_meter/kernel_detector/__init__.py diff --git a/nn_meter/kerneldetection/detection/__init__.py b/nn_meter/kernel_detector/detection/__init__.py similarity index 100% rename from nn_meter/kerneldetection/detection/__init__.py rename to nn_meter/kernel_detector/detection/__init__.py diff --git a/nn_meter/kerneldetection/detection/detector.py b/nn_meter/kernel_detector/detection/detector.py similarity index 93% rename from nn_meter/kerneldetection/detection/detector.py rename to nn_meter/kernel_detector/detection/detector.py index ab650b13..87991296 100644 --- a/nn_meter/kerneldetection/detection/detector.py +++ b/nn_meter/kernel_detector/detection/detector.py @@ -1,10 +1,10 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.kerneldetection.rulelib.rule_reader import RuleReader -from nn_meter.kerneldetection.rulelib.rule_splitter import RuleSplitter +from nn_meter.kernel_detector.rulelib.rule_reader import RuleReader +from nn_meter.kernel_detector.rulelib.rule_splitter import RuleSplitter from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kerneldetection.utils.constants import DUMMY_TYPES -from nn_meter.kerneldetection.utils.ir_tools import convert_nodes +from nn_meter.kernel_detector.utils.constants import DUMMY_TYPES +from nn_meter.kernel_detector.utils.ir_tools import convert_nodes # import logging diff --git a/nn_meter/kerneldetection/fusionlib/__init__.py b/nn_meter/kernel_detector/fusionlib/__init__.py similarity index 100% rename from nn_meter/kerneldetection/fusionlib/__init__.py rename to nn_meter/kernel_detector/fusionlib/__init__.py diff --git a/nn_meter/kerneldetection/fusionlib/add-relu_fusionunit.json b/nn_meter/kernel_detector/fusionlib/add-relu_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/add-relu_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/add-relu_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/bn-relu_fusionunit.json b/nn_meter/kernel_detector/fusionlib/bn-relu_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/bn-relu_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/bn-relu_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/channelshuffle_fusionunit.json b/nn_meter/kernel_detector/fusionlib/channelshuffle_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/channelshuffle_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/channelshuffle_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/conv-bn-relu_fusionunit.json b/nn_meter/kernel_detector/fusionlib/conv-bn-relu_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/conv-bn-relu_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/conv-bn-relu_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/conv-bn_fusionunit.json b/nn_meter/kernel_detector/fusionlib/conv-bn_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/conv-bn_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/conv-bn_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/dwconv-bn-relu_fusionunit.json b/nn_meter/kernel_detector/fusionlib/dwconv-bn-relu_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/dwconv-bn-relu_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/dwconv-bn-relu_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/elewise_fusionunit.json b/nn_meter/kernel_detector/fusionlib/elewise_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/elewise_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/elewise_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/gap_fusionunit.json b/nn_meter/kernel_detector/fusionlib/gap_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/gap_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/gap_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/hswish_fusionunit.json b/nn_meter/kernel_detector/fusionlib/hswish_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/hswish_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/hswish_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/se_fusionunit.json b/nn_meter/kernel_detector/fusionlib/se_fusionunit.json similarity index 100% rename from nn_meter/kerneldetection/fusionlib/se_fusionunit.json rename to nn_meter/kernel_detector/fusionlib/se_fusionunit.json diff --git a/nn_meter/kerneldetection/fusionlib/utils.py b/nn_meter/kernel_detector/fusionlib/utils.py similarity index 88% rename from nn_meter/kerneldetection/fusionlib/utils.py rename to nn_meter/kernel_detector/fusionlib/utils.py index 9e9f6f32..7450aae3 100644 --- a/nn_meter/kerneldetection/fusionlib/utils.py +++ b/nn_meter/kernel_detector/fusionlib/utils.py @@ -3,7 +3,7 @@ import os import json from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kerneldetection.utils.ir_tools import convert_nodes +from nn_meter.kernel_detector.utils.ir_tools import convert_nodes BASE_DIR = os.path.dirname(os.path.abspath(__file__)) diff --git a/nn_meter/kerneldetection/rulelib/__init__.py b/nn_meter/kernel_detector/rulelib/__init__.py similarity index 100% rename from nn_meter/kerneldetection/rulelib/__init__.py rename to nn_meter/kernel_detector/rulelib/__init__.py diff --git a/nn_meter/kerneldetection/rulelib/rule_reader.py b/nn_meter/kernel_detector/rulelib/rule_reader.py similarity index 96% rename from nn_meter/kerneldetection/rulelib/rule_reader.py rename to nn_meter/kernel_detector/rulelib/rule_reader.py index 62da24c8..8bb54c0c 100644 --- a/nn_meter/kerneldetection/rulelib/rule_reader.py +++ b/nn_meter/kernel_detector/rulelib/rule_reader.py @@ -2,7 +2,7 @@ # Licensed under the MIT license. import json from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kerneldetection.fusionlib import get_fusion_unit +from nn_meter.kernel_detector.fusionlib import get_fusion_unit class RuleReader: diff --git a/nn_meter/kerneldetection/rulelib/rule_splitter.py b/nn_meter/kernel_detector/rulelib/rule_splitter.py similarity index 95% rename from nn_meter/kerneldetection/rulelib/rule_splitter.py rename to nn_meter/kernel_detector/rulelib/rule_splitter.py index 7d4971bd..dac4446a 100644 --- a/nn_meter/kerneldetection/rulelib/rule_splitter.py +++ b/nn_meter/kernel_detector/rulelib/rule_splitter.py @@ -2,8 +2,8 @@ # Licensed under the MIT license. from .rule_reader import RuleReader from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kerneldetection.utils.match_helper import MatchHelper -from nn_meter.kerneldetection.utils.fusion_aware_graph import FusionAwareGraph +from nn_meter.kernel_detector.utils.match_helper import MatchHelper +from nn_meter.kernel_detector.utils.fusion_aware_graph import FusionAwareGraph class RuleSplitter: diff --git a/nn_meter/kerneldetection/utils/__init__.py b/nn_meter/kernel_detector/utils/__init__.py similarity index 100% rename from nn_meter/kerneldetection/utils/__init__.py rename to nn_meter/kernel_detector/utils/__init__.py diff --git a/nn_meter/kerneldetection/utils/constants.py b/nn_meter/kernel_detector/utils/constants.py similarity index 100% rename from nn_meter/kerneldetection/utils/constants.py rename to nn_meter/kernel_detector/utils/constants.py diff --git a/nn_meter/kerneldetection/utils/fusion_aware_graph.py b/nn_meter/kernel_detector/utils/fusion_aware_graph.py similarity index 100% rename from nn_meter/kerneldetection/utils/fusion_aware_graph.py rename to nn_meter/kernel_detector/utils/fusion_aware_graph.py diff --git a/nn_meter/kerneldetection/utils/ir_tools.py b/nn_meter/kernel_detector/utils/ir_tools.py similarity index 100% rename from nn_meter/kerneldetection/utils/ir_tools.py rename to nn_meter/kernel_detector/utils/ir_tools.py diff --git a/nn_meter/kerneldetection/utils/match_helper.py b/nn_meter/kernel_detector/utils/match_helper.py similarity index 100% rename from nn_meter/kerneldetection/utils/match_helper.py rename to nn_meter/kernel_detector/utils/match_helper.py diff --git a/nn_meter/kerneldetection/utils/union_find.py b/nn_meter/kernel_detector/utils/union_find.py similarity index 100% rename from nn_meter/kerneldetection/utils/union_find.py rename to nn_meter/kernel_detector/utils/union_find.py diff --git a/nn_meter/prediction/__init__.py b/nn_meter/predictor/__init__.py similarity index 100% rename from nn_meter/prediction/__init__.py rename to nn_meter/predictor/__init__.py diff --git a/nn_meter/nn_meter.py b/nn_meter/predictor/nn_meter_predictor.py similarity index 68% rename from nn_meter/nn_meter.py rename to nn_meter/predictor/nn_meter_predictor.py index fa384549..0cdc99b0 100644 --- a/nn_meter/nn_meter.py +++ b/nn_meter/predictor/nn_meter_predictor.py @@ -1,10 +1,10 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. from glob import glob -from nn_meter.prediction.predictors.predict_by_kernel import nn_predict -from nn_meter.kerneldetection import KernelDetector -from nn_meter.ir_converters import model_file_to_graph, model_to_graph -from nn_meter.prediction.load_predictors import loading_to_local +from nn_meter.predictor.predictors.predict_by_kernel import nn_predict +from nn_meter.kernel_detector import KernelDetector +from nn_meter.ir_converter import model_file_to_graph, model_to_graph +from .utils import loading_to_local import yaml import os @@ -12,66 +12,11 @@ from shutil import copyfile from packaging import version import logging - -__user_config_folder__ = os.path.expanduser('~/.nn_meter/config') -__default_user_data_folder__ = os.path.expanduser('~/.nn_meter/data') +from nn_meter.utils import load_config_file, get_user_data_folder __predictors_cfg_filename__ = 'predictors.yaml' -def create_user_configs(): - """create user configs from distributed configs - """ - os.makedirs(__user_config_folder__, exist_ok=True) - # TODO/backlog: to handle config merging when upgrading - for f in pkg_resources.resource_listdir(__name__, 'configs'): - copyfile(pkg_resources.resource_filename(__name__, f'configs/{f}'), os.path.join(__user_config_folder__, f)) - # make default setting yaml file - with open(os.path.join(__user_config_folder__, 'settings.yaml'), 'w') as fp: - yaml.dump({'data_folder': __default_user_data_folder__}, fp) - - -def get_user_data_folder(): - """get user data folder in settings.yaml - """ - filepath = os.path.join(__user_config_folder__, 'settings.yaml') - try: - with open(filepath) as fp: - return os.path.join(yaml.load(fp, yaml.FullLoader)['data_folder']) - except FileNotFoundError: - logging.info(f"setting file {filepath} not found, created") - create_user_configs() - return get_user_data_folder() - - -def change_user_data_folder(new_folder): - """change user data folder in settings.yaml - """ - os.makedirs(new_folder, exist_ok=True) - with open(os.path.join(__user_config_folder__, 'settings.yaml')) as fp: - setting = yaml.load(fp, yaml.FullLoader) - with open(os.path.join(__user_config_folder__, 'settings.yaml'), 'w') as fp: - setting['data_folder'] = new_folder - yaml.dump(setting, fp) - - -def load_config_file(fname: str, loader=None): - """load config file from __user_config_folder__; - if the file not located in __user_config_folder__, copy it from distribution - """ - filepath = os.path.join(__user_config_folder__, fname) - try: - with open(filepath) as fp: - if loader is None: - return yaml.load(fp, yaml.FullLoader) - else: - return loader(fp) - except FileNotFoundError: - logging.info(f"config file {filepath} not found, created") - create_user_configs() - return load_config_file(fname) - - def list_latency_predictors(): """return the list of latency predictors specified in nn_meter/configs/predictors.yaml """ @@ -121,10 +66,10 @@ def load_latency_predictor(predictor_name: str, predictor_version: float = None) user_data_folder = get_user_data_folder() pred_info = load_predictor_config(predictor_name, predictor_version) kernel_predictors, fusionrule = loading_to_local(pred_info, os.path.join(user_data_folder, 'predictor')) - return nnMeter(kernel_predictors, fusionrule) + return nnMeterPredictor(kernel_predictors, fusionrule) -class nnMeter: +class nnMeterPredictor: def __init__(self, predictors, fusionrule): self.kernel_predictors = predictors self.fusionrule = fusionrule diff --git a/nn_meter/prediction/predictors/__init__.py b/nn_meter/predictor/predictors/__init__.py similarity index 100% rename from nn_meter/prediction/predictors/__init__.py rename to nn_meter/predictor/predictors/__init__.py diff --git a/nn_meter/prediction/predictors/extract_feature.py b/nn_meter/predictor/predictors/extract_feature.py similarity index 100% rename from nn_meter/prediction/predictors/extract_feature.py rename to nn_meter/predictor/predictors/extract_feature.py diff --git a/nn_meter/prediction/predictors/kernel_predictor.py b/nn_meter/predictor/predictors/kernel_predictor.py similarity index 100% rename from nn_meter/prediction/predictors/kernel_predictor.py rename to nn_meter/predictor/predictors/kernel_predictor.py diff --git a/nn_meter/prediction/predictors/predict_by_kernel.py b/nn_meter/predictor/predictors/predict_by_kernel.py similarity index 100% rename from nn_meter/prediction/predictors/predict_by_kernel.py rename to nn_meter/predictor/predictors/predict_by_kernel.py diff --git a/nn_meter/prediction/predictors/utils.py b/nn_meter/predictor/predictors/utils.py similarity index 100% rename from nn_meter/prediction/predictors/utils.py rename to nn_meter/predictor/predictors/utils.py diff --git a/nn_meter/prediction/load_predictors.py b/nn_meter/predictor/utils.py similarity index 100% rename from nn_meter/prediction/load_predictors.py rename to nn_meter/predictor/utils.py diff --git a/nn_meter/utils/__init__.py b/nn_meter/utils/__init__.py index 9a045456..b8d46620 100644 --- a/nn_meter/utils/__init__.py +++ b/nn_meter/utils/__init__.py @@ -1,2 +1,8 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. +from config_manager import ( + create_user_configs, + get_user_data_folder, + change_user_data_folder, + load_config_file +) \ No newline at end of file diff --git a/nn_meter/utils/config_manager.py b/nn_meter/utils/config_manager.py new file mode 100644 index 00000000..d1ca03d5 --- /dev/null +++ b/nn_meter/utils/config_manager.py @@ -0,0 +1,69 @@ +from glob import glob +from nn_meter.predictor.predictors.predict_by_kernel import nn_predict +from nn_meter.kernel_detector import KernelDetector +from nn_meter.ir_converter import model_file_to_graph, model_to_graph +from nn_meter.predictor.load_predictors import loading_to_local + +import yaml +import os +import pkg_resources +from shutil import copyfile +import logging + +__user_config_folder__ = os.path.expanduser('~/.nn_meter/config') +__default_user_data_folder__ = os.path.expanduser('~/.nn_meter/data') + +__predictors_cfg_filename__ = 'predictors.yaml' + + +def create_user_configs(): + """create user configs from distributed configs + """ + os.makedirs(__user_config_folder__, exist_ok=True) + # TODO/backlog: to handle config merging when upgrading + for f in pkg_resources.resource_listdir(__name__, 'configs'): + copyfile(pkg_resources.resource_filename(__name__, f'configs/{f}'), os.path.join(__user_config_folder__, f)) + # make default setting yaml file + with open(os.path.join(__user_config_folder__, 'settings.yaml'), 'w') as fp: + yaml.dump({'data_folder': __default_user_data_folder__}, fp) + + +def get_user_data_folder(): + """get user data folder in settings.yaml + """ + filepath = os.path.join(__user_config_folder__, 'settings.yaml') + try: + with open(filepath) as fp: + return os.path.join(yaml.load(fp, yaml.FullLoader)['data_folder']) + except FileNotFoundError: + logging.info(f"setting file {filepath} not found, created") + create_user_configs() + return get_user_data_folder() + + +def change_user_data_folder(new_folder): + """change user data folder in settings.yaml + """ + os.makedirs(new_folder, exist_ok=True) + with open(os.path.join(__user_config_folder__, 'settings.yaml')) as fp: + setting = yaml.load(fp, yaml.FullLoader) + with open(os.path.join(__user_config_folder__, 'settings.yaml'), 'w') as fp: + setting['data_folder'] = new_folder + yaml.dump(setting, fp) + + +def load_config_file(fname: str, loader=None): + """load config file from __user_config_folder__; + if the file not located in __user_config_folder__, copy it from distribution + """ + filepath = os.path.join(__user_config_folder__, fname) + try: + with open(filepath) as fp: + if loader is None: + return yaml.load(fp, yaml.FullLoader) + else: + return loader(fp) + except FileNotFoundError: + logging.info(f"config file {filepath} not found, created") + create_user_configs() + return load_config_file(fname) \ No newline at end of file diff --git a/nn_meter/utils/import_package.py b/nn_meter/utils/import_package.py new file mode 100644 index 00000000..f41def33 --- /dev/null +++ b/nn_meter/utils/import_package.py @@ -0,0 +1,78 @@ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT license. +from packaging import version +import logging + + +def try_import_onnx(require_version = ["1.9.0"]): + if isinstance(require_version, str): + require_version = [require_version] + try: + import onnx + if version.parse(onnx.__version__).release not in [version.parse(v).release for v in require_version]: + logging.warning(f'onnx=={onnx.__version__} is not well tested now, well tested version: onnx=={", ".join(require_version)}' ) + return onnx + except ImportError: + logging.error(f'You have not install the onnx package, please install onnx=={require_version[0]} and try again.') + exit() + +def try_import_torch(require_version = ["1.9.0", "1.7.1"]): + if isinstance(require_version, str): + require_version = [require_version] + try: + import torch + if version.parse(torch.__version__).release not in [version.parse(v).release for v in require_version]: + logging.warning(f'torch=={torch.__version__} is not well tested now, well tested version: torch=={", ".join(require_version)}' ) + return torch + except ImportError: + logging.error(f'You have not install the torch package, please install torch=={require_version[0]} and try again.') + exit() + +def try_import_tensorflow(require_version = ["1.15.0"]): + if isinstance(require_version, str): + require_version = [require_version] + try: + import tensorflow + if version.parse(tensorflow.__version__).release not in [version.parse(v).release for v in require_version]: + logging.warning(f'tensorflow=={tensorflow.__version__} is not well tested now, well tested version: tensorflow=={", ".join(require_version)}' ) + return tensorflow + except ImportError: + logging.error(f'You have not install the tensorflow package, please install tensorflow=={require_version[0]} and try again.') + exit() + +def try_import_nni(require_version = ["2.4", "2.5"]): + if isinstance(require_version, str): + require_version = [require_version] + try: + import nni + if version.parse(nni.__version__).release not in [version.parse(v).release for v in require_version]: + logging.warning(f'nni=={nni.__version__} is not well tested now, well tested version: nni=={", ".join(require_version)}' ) + return nni + except ImportError: + logging.error(f'You have not install the tensorflow package, please install tensorflow=={require_version[0]} and try again.') + exit() + +def try_import_torchvision_models(): + try: + import torchvision + return torchvision.models + except ImportError: + logging.error(f'You have not install the torchvision package, please install torchvision and try again.') + exit() + +def try_import_onnxsim(): + try: + from onnxsim import simplify + return simplify + except ImportError: + logging.error(f'You have not install the onnx-simplifier package, please install onnx-simplifier and try again.') + exit() + +def try_import_dgl(): + try: + import dgl + return dgl + except ImportError: + logging.error(f'You have not install the dgl package, please install dgl and try again.') + exit() + \ No newline at end of file diff --git a/nn_meter/utils/utils.py b/nn_meter/utils/utils.py index f9b61926..c7e7649e 100644 --- a/nn_meter/utils/utils.py +++ b/nn_meter/utils/utils.py @@ -4,7 +4,6 @@ from zipfile import ZipFile from tqdm import tqdm import requests -from packaging import version import logging @@ -36,75 +35,3 @@ def download_from_url(urladdr, ppath): progress_bar.close() os.remove(file_name) -def try_import_onnx(require_version = ["1.9.0"]): - if isinstance(require_version, str): - require_version = [require_version] - try: - import onnx - if version.parse(onnx.__version__).release not in [version.parse(v).release for v in require_version]: - logging.warning(f'onnx=={onnx.__version__} is not well tested now, well tested version: onnx=={", ".join(require_version)}' ) - return onnx - except ImportError: - logging.error(f'You have not install the onnx package, please install onnx=={require_version[0]} and try again.') - exit() - -def try_import_torch(require_version = ["1.9.0", "1.7.1"]): - if isinstance(require_version, str): - require_version = [require_version] - try: - import torch - if version.parse(torch.__version__).release not in [version.parse(v).release for v in require_version]: - logging.warning(f'torch=={torch.__version__} is not well tested now, well tested version: torch=={", ".join(require_version)}' ) - return torch - except ImportError: - logging.error(f'You have not install the torch package, please install torch=={require_version[0]} and try again.') - exit() - -def try_import_tensorflow(require_version = ["1.15.0"]): - if isinstance(require_version, str): - require_version = [require_version] - try: - import tensorflow - if version.parse(tensorflow.__version__).release not in [version.parse(v).release for v in require_version]: - logging.warning(f'tensorflow=={tensorflow.__version__} is not well tested now, well tested version: tensorflow=={", ".join(require_version)}' ) - return tensorflow - except ImportError: - logging.error(f'You have not install the tensorflow package, please install tensorflow=={require_version[0]} and try again.') - exit() - -def try_import_nni(require_version = ["2.4", "2.5"]): - if isinstance(require_version, str): - require_version = [require_version] - try: - import nni - if version.parse(nni.__version__).release not in [version.parse(v).release for v in require_version]: - logging.warning(f'nni=={nni.__version__} is not well tested now, well tested version: nni=={", ".join(require_version)}' ) - return nni - except ImportError: - logging.error(f'You have not install the tensorflow package, please install tensorflow=={require_version[0]} and try again.') - exit() - -def try_import_torchvision_models(): - try: - import torchvision - return torchvision.models - except ImportError: - logging.error(f'You have not install the torchvision package, please install torchvision and try again.') - exit() - -def try_import_onnxsim(): - try: - from onnxsim import simplify - return simplify - except ImportError: - logging.error(f'You have not install the onnx-simplifier package, please install onnx-simplifier and try again.') - exit() - -def try_import_dgl(): - try: - import dgl - return dgl - except ImportError: - logging.error(f'You have not install the dgl package, please install dgl and try again.') - exit() - \ No newline at end of file diff --git a/setup.py b/setup.py index ce0f12fb..46d98862 100644 --- a/setup.py +++ b/setup.py @@ -26,7 +26,7 @@ ], packages=find_packages(), package_data={ - 'nn_meter': ['configs/*.yaml', 'kerneldetection/fusionlib/*.json'], + 'nn_meter': ['configs/*.yaml', 'kernel_detector/fusionlib/*.json'], }, entry_points={ 'console_scripts': ['nn-meter=nn_meter.nn_meter_cli:nn_meter_cli'], From 72eee00c082ccfe64c4b357ec246f4144e36c7fe Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 10:36:03 +0800 Subject: [PATCH 02/18] refine package import --- .../hardware-aware-model-design.md | 74 +++++++++---------- docs/{ => predictor}/usage.md | 0 .../requirements} | 0 nn_meter/__init__.py | 22 ++++-- nn_meter/dataset/bench_dataset.py | 9 +-- nn_meter/dataset/gnn_dataloader.py | 10 ++- .../frozenpb_converter/frozenpb_converter.py | 2 +- .../frozenpb_converter/frozenpb_parser.py | 9 ++- .../frozenpb_converter/shape_fetcher.py | 3 +- .../frozenpb_converter/shape_inference.py | 2 +- .../ir_converter/onnx_converter/converter.py | 6 +- nn_meter/ir_converter/onnx_converter/utils.py | 2 - .../ir_converter/torch_converter/converter.py | 6 +- nn_meter/ir_converter/utils.py | 5 +- nn_meter/kernel_detector/__init__.py | 2 +- .../kernel_detector/detection/__init__.py | 2 - nn_meter/kernel_detector/fusionlib/utils.py | 2 +- .../detector.py => kernel_detector.py} | 9 +-- .../kernel_detector/rulelib/rule_reader.py | 2 +- .../kernel_detector/rulelib/rule_splitter.py | 4 +- .../utils/fusion_aware_graph.py | 4 +- nn_meter/nn_meter_cli.py | 8 +- nn_meter/predictor/__init__.py | 5 +- nn_meter/predictor/nn_meter_predictor.py | 14 ++-- .../{predictors => prediction}/__init__.py | 0 .../extract_feature.py | 2 +- .../kernel_predictor.py | 0 .../predict_by_kernel.py | 0 .../{predictors => prediction}/utils.py | 3 +- nn_meter/predictor/utils.py | 2 +- nn_meter/utils/__init__.py | 3 +- nn_meter/utils/config_manager.py | 9 +-- nn_meter/utils/import_package.py | 2 +- nn_meter/utils/utils.py | 2 +- 34 files changed, 110 insertions(+), 115 deletions(-) rename docs/{ => predictor}/hardware-aware-model-design.md (99%) rename docs/{ => predictor}/usage.md (100%) rename docs/{requirements.txt => requirements/requirements} (100%) delete mode 100644 nn_meter/kernel_detector/detection/__init__.py rename nn_meter/kernel_detector/{detection/detector.py => kernel_detector.py} (92%) rename nn_meter/predictor/{predictors => prediction}/__init__.py (100%) rename nn_meter/predictor/{predictors => prediction}/extract_feature.py (100%) rename nn_meter/predictor/{predictors => prediction}/kernel_predictor.py (100%) rename nn_meter/predictor/{predictors => prediction}/predict_by_kernel.py (100%) rename nn_meter/predictor/{predictors => prediction}/utils.py (99%) diff --git a/docs/hardware-aware-model-design.md b/docs/predictor/hardware-aware-model-design.md similarity index 99% rename from docs/hardware-aware-model-design.md rename to docs/predictor/hardware-aware-model-design.md index e8586756..efcfbcd6 100644 --- a/docs/hardware-aware-model-design.md +++ b/docs/predictor/hardware-aware-model-design.md @@ -1,37 +1,37 @@ -# Hardware-aware DNN Model Design - -In many DNN model deployment scenarios, there are strict inference efficiency constraints as well as the model accuracy. For example, the **inference latency** and **energy consumption** are the most frequently used criteria of efficiencies to determine whether a DNN model could be deployed on a mobile phone or not. Therefore, DNN model designers have to consider the model efficiency. A typical methodology is to train a big model to meet the accuracy requirements first, and then apply model compression algorithms to get a light-weight model with similar accuracy but much smaller size. Due to many reasons, they use the number of parameters and FLOPs in the compression process. - -However, as pointed out in our work [[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) and many others, ***neither number of parameters nor number of FLOPs is a good metric of the real inference efficiency (e.g., latency or energy consumption)***. Operators with similar FLOPs may have very different inference latency on different hardware platforms (e.g., CPU, GPU, and ASIC) (shown in work [[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) and [[3]](https://proceedings.mlsys.org/paper/2021/file/02522a2b2726fb0a03bb19f2d8d9524d-Paper.pdf)). This makes the effort of designing efficient DNN models for a target hardware bit of games of opening blind boxes. Recently, many hardware-aware NAS works are proposed to solve this challenge. - -Compared with the conventional NAS algorithms, some recent works (i.e. hardware-aware NAS, aka HW-NAS) integrated hardware-awareness into the search loop and achieves a balanced trade-off between accuracy and hardware efficiencies [[4]](http://arxiv.org/abs/2101.09336). - -Next, we introduce our hardware-aware NAS framework[[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf), which combines the nn-Meter, to search high-accuracy DNN models within the latency constraints for target edge devices. - -## Hardware-aware Neural Architecture Search - -drawing - -**Hardware-aware Search Space Generation.** As formulated in many works, the search space is one of the three key aspects of a NAS process (the other two are the search strategy and the evaluation methodology) and matters a lot to the final results. - -Our HW-NAS framework firstly automatically selects the hardware-friendly operators (or blocks) by considering both representation capacity and hardware efficiency. The selected operators could establish a ***hardware-aware search space*** for most of existing NAS algorithms. - -**Latency Prediction in search process by nn-Meter.** Different with other simple predictors (e.g., look-up table for operators/blocks, linear regression models), [nn-Meter](overview.md) conducts kernel-level prediction, which captures the complex model graph optimizations on edge devices. nn-Meter is the first accurate latency prediction tool for DNNs on edge devices. - -Besides the search space specialization, our HW-NAS framework also allows combining nn-Meter with existing NAS algorithms in the optimization objectives and constraints. As described in [[4]](http://arxiv.org/abs/2101.09336), the HW-NAS algorithms often consider hardware efficiency metrics as the constraints of existing NAS formulation or part of the scalarized loss functions (e.g., the loss is weighted sum of both cross entropy loss and hardware-aware penalty). Since the NAS process may sample up to millions of candidate model architectures, the obtaining of hardware metrics must be accurate and efficient. - -nn-Meter is now integrated with [NNI](https://github.com/microsoft/nni), the AutoML framework also published by Microsoft, and could be combined with existing NAS algorithms seamlessly. [This doc](https://nni.readthedocs.io/en/stable/NAS/multi_trial_nas.html) show how to construct a latency constraint filter in [random search algorithm](https://arxiv.org/abs/1902.07638) on [SPOS NAS](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123610528.pdf) search space. Users could use this filter in multiple phases of the NAS process, e.g., the architecture searching phase and the super-net training phase. - -***Note that current nn-Meter project is limited to the latency prediction. For the other hardware metrics, e.g., energy consumption is another important metric in edge computing. Collaborations and contributions together with nn-Meter are highly welcomed!*** - -## Other hardware-aware techniques - -Besides light weighted NAS, which search for an efficient architecture directly, there are also other techniques to achieve light weight DNN models, such as model compression and knowledge distillation (KD). Both methods tries to get a smaller but similar-performed models from a pre-trained big model. The difference is that model compression removes some of the components in the origin model, while knowledge distillation constructs a new student model and lets it learn the behavior of the origin model. Hardware awareness could also be combined with these methods. -For example, nn-Meter could help users to construct suitable student architectures for the target hardware platform in the KD task. - -## References - -1. Li Lyna Zhang, Yuqing Yang, Yuhang Jiang, Wenwu Zhu, Yunxin Liu: ["Fast hardware-aware neural architecture search."](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020. -2. Li Lyna Zhang, Shihao Han, Jianyu Wei, Ningxin Zheng, Ting Cao, Yuqing Yang, Yunxin Liu: ["nn-Meter: Towards Accurate Latency Prediction of Deep-Learning Model Inference on Diverse Edge Devices."](https://dl.acm.org/doi/10.1145/3458864.3467882) Proceedings of the 19th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys 2021) -3. Xiaohu Tang, Shihao Han, Li Lyna Zhang, Ting Cao, Yunxin Liu: ["To Bridge Neural Network Design and Real-World Performance: A Behaviour Study for Neural Networks"](https://proceedings.mlsys.org/paper/2021/file/02522a2b2726fb0a03bb19f2d8d9524d-Paper.pdf) Proceedings of the 4th MLSys Conference (MLSys 2021) -4. Benmeziane, H., Maghraoui, K. el, Ouarnoughi, H., Niar, S., Wistuba, M., & Wang, N. (2021).[" A Comprehensive Survey on Hardware-Aware Neural Architecture Search."](http://arxiv.org/abs/2101.09336) +# Hardware-aware DNN Model Design + +In many DNN model deployment scenarios, there are strict inference efficiency constraints as well as the model accuracy. For example, the **inference latency** and **energy consumption** are the most frequently used criteria of efficiencies to determine whether a DNN model could be deployed on a mobile phone or not. Therefore, DNN model designers have to consider the model efficiency. A typical methodology is to train a big model to meet the accuracy requirements first, and then apply model compression algorithms to get a light-weight model with similar accuracy but much smaller size. Due to many reasons, they use the number of parameters and FLOPs in the compression process. + +However, as pointed out in our work [[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) and many others, ***neither number of parameters nor number of FLOPs is a good metric of the real inference efficiency (e.g., latency or energy consumption)***. Operators with similar FLOPs may have very different inference latency on different hardware platforms (e.g., CPU, GPU, and ASIC) (shown in work [[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) and [[3]](https://proceedings.mlsys.org/paper/2021/file/02522a2b2726fb0a03bb19f2d8d9524d-Paper.pdf)). This makes the effort of designing efficient DNN models for a target hardware bit of games of opening blind boxes. Recently, many hardware-aware NAS works are proposed to solve this challenge. + +Compared with the conventional NAS algorithms, some recent works (i.e. hardware-aware NAS, aka HW-NAS) integrated hardware-awareness into the search loop and achieves a balanced trade-off between accuracy and hardware efficiencies [[4]](http://arxiv.org/abs/2101.09336). + +Next, we introduce our hardware-aware NAS framework[[1]](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf), which combines the nn-Meter, to search high-accuracy DNN models within the latency constraints for target edge devices. + +## Hardware-aware Neural Architecture Search + +drawing + +**Hardware-aware Search Space Generation.** As formulated in many works, the search space is one of the three key aspects of a NAS process (the other two are the search strategy and the evaluation methodology) and matters a lot to the final results. + +Our HW-NAS framework firstly automatically selects the hardware-friendly operators (or blocks) by considering both representation capacity and hardware efficiency. The selected operators could establish a ***hardware-aware search space*** for most of existing NAS algorithms. + +**Latency Prediction in search process by nn-Meter.** Different with other simple predictors (e.g., look-up table for operators/blocks, linear regression models), [nn-Meter](overview.md) conducts kernel-level prediction, which captures the complex model graph optimizations on edge devices. nn-Meter is the first accurate latency prediction tool for DNNs on edge devices. + +Besides the search space specialization, our HW-NAS framework also allows combining nn-Meter with existing NAS algorithms in the optimization objectives and constraints. As described in [[4]](http://arxiv.org/abs/2101.09336), the HW-NAS algorithms often consider hardware efficiency metrics as the constraints of existing NAS formulation or part of the scalarized loss functions (e.g., the loss is weighted sum of both cross entropy loss and hardware-aware penalty). Since the NAS process may sample up to millions of candidate model architectures, the obtaining of hardware metrics must be accurate and efficient. + +nn-Meter is now integrated with [NNI](https://github.com/microsoft/nni), the AutoML framework also published by Microsoft, and could be combined with existing NAS algorithms seamlessly. [This doc](https://nni.readthedocs.io/en/stable/NAS/multi_trial_nas.html) show how to construct a latency constraint filter in [random search algorithm](https://arxiv.org/abs/1902.07638) on [SPOS NAS](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123610528.pdf) search space. Users could use this filter in multiple phases of the NAS process, e.g., the architecture searching phase and the super-net training phase. + +***Note that current nn-Meter project is limited to the latency prediction. For the other hardware metrics, e.g., energy consumption is another important metric in edge computing. Collaborations and contributions together with nn-Meter are highly welcomed!*** + +## Other hardware-aware techniques + +Besides light weighted NAS, which search for an efficient architecture directly, there are also other techniques to achieve light weight DNN models, such as model compression and knowledge distillation (KD). Both methods tries to get a smaller but similar-performed models from a pre-trained big model. The difference is that model compression removes some of the components in the origin model, while knowledge distillation constructs a new student model and lets it learn the behavior of the origin model. Hardware awareness could also be combined with these methods. +For example, nn-Meter could help users to construct suitable student architectures for the target hardware platform in the KD task. + +## References + +1. Li Lyna Zhang, Yuqing Yang, Yuhang Jiang, Wenwu Zhu, Yunxin Liu: ["Fast hardware-aware neural architecture search."](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w40/Zhang_Fast_Hardware-Aware_Neural_Architecture_Search_CVPRW_2020_paper.pdf) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020. +2. Li Lyna Zhang, Shihao Han, Jianyu Wei, Ningxin Zheng, Ting Cao, Yuqing Yang, Yunxin Liu: ["nn-Meter: Towards Accurate Latency Prediction of Deep-Learning Model Inference on Diverse Edge Devices."](https://dl.acm.org/doi/10.1145/3458864.3467882) Proceedings of the 19th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys 2021) +3. Xiaohu Tang, Shihao Han, Li Lyna Zhang, Ting Cao, Yunxin Liu: ["To Bridge Neural Network Design and Real-World Performance: A Behaviour Study for Neural Networks"](https://proceedings.mlsys.org/paper/2021/file/02522a2b2726fb0a03bb19f2d8d9524d-Paper.pdf) Proceedings of the 4th MLSys Conference (MLSys 2021) +4. Benmeziane, H., Maghraoui, K. el, Ouarnoughi, H., Niar, S., Wistuba, M., & Wang, N. (2021).[" A Comprehensive Survey on Hardware-Aware Neural Architecture Search."](http://arxiv.org/abs/2101.09336) diff --git a/docs/usage.md b/docs/predictor/usage.md similarity index 100% rename from docs/usage.md rename to docs/predictor/usage.md diff --git a/docs/requirements.txt b/docs/requirements/requirements similarity index 100% rename from docs/requirements.txt rename to docs/requirements/requirements diff --git a/nn_meter/__init__.py b/nn_meter/__init__.py index 2efbcef2..48740fba 100644 --- a/nn_meter/__init__.py +++ b/nn_meter/__init__.py @@ -7,20 +7,26 @@ except ModuleNotFoundError: __version__ = 'UNKNOWN' -from .nn_meter import ( - nnMeter, +import logging +from functools import partial, partialmethod + +from .predictor import ( + nnMeterPredictor, load_latency_predictor, list_latency_predictors, + latency_metrics +) +from .ir_converter import ( model_file_to_graph, - model_to_graph, + model_to_graph +) +from .utils import ( create_user_configs, change_user_data_folder ) -from .utils.utils import download_from_url -from .predictor import latency_metrics -from .dataset import bench_dataset # TODO: add GNNDataloader and GNNDataset here @wenxuan -import logging -from functools import partial, partialmethod +from .dataset import bench_dataset +from .utils import download_from_url + logging.KEYINFO = 22 logging.addLevelName(logging.KEYINFO, 'KEYINFO') diff --git a/nn_meter/dataset/bench_dataset.py b/nn_meter/dataset/bench_dataset.py index 7e2b2249..428fe780 100644 --- a/nn_meter/dataset/bench_dataset.py +++ b/nn_meter/dataset/bench_dataset.py @@ -1,13 +1,12 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. import os, sys -from nn_meter.predictor import latency_metrics +import logging +import jsonlines from glob import glob -from nn_meter.nn_meter import list_latency_predictors, load_latency_predictor, get_user_data_folder -from nn_meter import download_from_url -import jsonlines -import logging +from nn_meter.predictor import latency_metrics, list_latency_predictors, load_latency_predictor +from nn_meter.utils import download_from_url, get_user_data_folder __user_dataset_folder__ = os.path.join(get_user_data_folder(), 'dataset') diff --git a/nn_meter/dataset/gnn_dataloader.py b/nn_meter/dataset/gnn_dataloader.py index 44c76ac6..33e5bab4 100644 --- a/nn_meter/dataset/gnn_dataloader.py +++ b/nn_meter/dataset/gnn_dataloader.py @@ -1,16 +1,18 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -import torch -import jsonlines import os import random +import torch +import jsonlines from .bench_dataset import bench_dataset -from nn_meter.nn_meter import get_user_data_folder -from nn_meter.utils.utils import try_import_dgl +from nn_meter.utils import get_user_data_folder +from nn_meter.utils.import_package import try_import_dgl + RAW_DATA_URL = "https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip" __user_dataset_folder__ = os.path.join(get_user_data_folder(), 'dataset') + hws = [ "cortexA76cpu_tflite21", "adreno640gpu_tflite21", diff --git a/nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py b/nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py index aac61a4e..34950490 100644 --- a/nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py +++ b/nn_meter/ir_converter/frozenpb_converter/frozenpb_converter.py @@ -2,10 +2,10 @@ # Licensed under the MIT license. import numpy as np -from nn_meter.utils.graph_tool import ModelGraph from .frozenpb_parser import FrozenPbParser from .shape_inference import ShapeInference from .shape_fetcher import ShapeFetcher +from nn_meter.utils.graph_tool import ModelGraph class FrozenPbConverter: def __init__(self, file_name): diff --git a/nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py b/nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py index 913a0510..479522c3 100644 --- a/nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py +++ b/nn_meter/ir_converter/frozenpb_converter/frozenpb_parser.py @@ -1,12 +1,13 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.utils.utils import try_import_tensorflow -from .protobuf_helper import ProtobufHelper -from .shape_fetcher import ShapeFetcher -import copy import re +import copy import logging +from .protobuf_helper import ProtobufHelper +from nn_meter.utils.import_package import try_import_tensorflow + + logging = logging.getLogger(__name__) diff --git a/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py b/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py index 9c2f594b..fc8caec4 100644 --- a/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py +++ b/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py @@ -1,9 +1,8 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.utils.utils import try_import_tensorflow import numpy as np from typing import List - +from nn_meter.utils.utils import try_import_tensorflow class ShapeFetcher: def __init__(self, input_graph): diff --git a/nn_meter/ir_converter/frozenpb_converter/shape_inference.py b/nn_meter/ir_converter/frozenpb_converter/shape_inference.py index f3b3dae0..da05d208 100644 --- a/nn_meter/ir_converter/frozenpb_converter/shape_inference.py +++ b/nn_meter/ir_converter/frozenpb_converter/shape_inference.py @@ -1,10 +1,10 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from .protobuf_helper import ProtobufHelper as ph from functools import reduce import copy import math import logging +from .protobuf_helper import ProtobufHelper as ph logging = logging.getLogger(__name__) diff --git a/nn_meter/ir_converter/onnx_converter/converter.py b/nn_meter/ir_converter/onnx_converter/converter.py index d4d214f9..04786f89 100644 --- a/nn_meter/ir_converter/onnx_converter/converter.py +++ b/nn_meter/ir_converter/onnx_converter/converter.py @@ -1,11 +1,11 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.utils.utils import try_import_onnx +import logging import networkx as nx +from itertools import chain from .utils import get_tensor_shape from .constants import SLICE_TYPE -from itertools import chain -import logging +from nn_meter.utils.import_package import try_import_onnx class OnnxConverter: diff --git a/nn_meter/ir_converter/onnx_converter/utils.py b/nn_meter/ir_converter/onnx_converter/utils.py index 9abe0452..172cc82b 100644 --- a/nn_meter/ir_converter/onnx_converter/utils.py +++ b/nn_meter/ir_converter/onnx_converter/utils.py @@ -1,7 +1,5 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. - - def get_tensor_shape(tensor): shape = [] for dim in tensor.type.tensor_type.shape.dim: diff --git a/nn_meter/ir_converter/torch_converter/converter.py b/nn_meter/ir_converter/torch_converter/converter.py index 1af2f43e..f595985b 100644 --- a/nn_meter/ir_converter/torch_converter/converter.py +++ b/nn_meter/ir_converter/torch_converter/converter.py @@ -1,11 +1,9 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.utils.utils import try_import_onnx, try_import_torch, try_import_onnxsim, try_import_nni import tempfile -from nn_meter.ir_converter.onnx_converter import OnnxConverter - - +from ..onnx_converter import OnnxConverter from .opset_map import nni_attr_map, nni_type_map +from nn_meter.utils.import_package import try_import_onnx, try_import_torch, try_import_onnxsim, try_import_nni def _nchw_to_nhwc(shapes): diff --git a/nn_meter/ir_converter/utils.py b/nn_meter/ir_converter/utils.py index d435835a..de6b9527 100644 --- a/nn_meter/ir_converter/utils.py +++ b/nn_meter/ir_converter/utils.py @@ -2,11 +2,12 @@ # Licensed under the MIT license. import json import logging -from nn_meter.utils.utils import try_import_onnx, try_import_torch, try_import_torchvision_models +from nn_meter.utils.import_package import try_import_onnx, try_import_torch, try_import_torchvision_models from .onnx_converter import OnnxConverter from .frozenpb_converter import FrozenPbConverter from .torch_converter import NNIBasedTorchConverter, OnnxBasedTorchConverter, NNIIRConverter + def model_file_to_graph(filename: str, model_type: str, input_shape=(1, 3, 224, 224), apply_nni=False): """ read the given file and convert the model in the file content to nn-Meter IR graph object @@ -106,10 +107,12 @@ def onnx_model_to_graph(model): converter = OnnxConverter(model) return converter.convert() + def nni_model_to_graph(model): converter = NNIIRConverter(model) return converter.convert() + def torch_model_to_graph(model, input_shape=(1, 3, 224, 224), apply_nni=False): torch = try_import_torch() args = torch.randn(*input_shape) diff --git a/nn_meter/kernel_detector/__init__.py b/nn_meter/kernel_detector/__init__.py index 2b31f4e7..bd89c7e5 100644 --- a/nn_meter/kernel_detector/__init__.py +++ b/nn_meter/kernel_detector/__init__.py @@ -1,3 +1,3 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from .detection.detector import KernelDetector +from .kernel_detector import KernelDetector diff --git a/nn_meter/kernel_detector/detection/__init__.py b/nn_meter/kernel_detector/detection/__init__.py deleted file mode 100644 index 9a045456..00000000 --- a/nn_meter/kernel_detector/detection/__init__.py +++ /dev/null @@ -1,2 +0,0 @@ -# Copyright (c) Microsoft Corporation. -# Licensed under the MIT license. diff --git a/nn_meter/kernel_detector/fusionlib/utils.py b/nn_meter/kernel_detector/fusionlib/utils.py index 7450aae3..2ba05023 100644 --- a/nn_meter/kernel_detector/fusionlib/utils.py +++ b/nn_meter/kernel_detector/fusionlib/utils.py @@ -3,7 +3,7 @@ import os import json from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kernel_detector.utils.ir_tools import convert_nodes +from ..utils.ir_tools import convert_nodes BASE_DIR = os.path.dirname(os.path.abspath(__file__)) diff --git a/nn_meter/kernel_detector/detection/detector.py b/nn_meter/kernel_detector/kernel_detector.py similarity index 92% rename from nn_meter/kernel_detector/detection/detector.py rename to nn_meter/kernel_detector/kernel_detector.py index 87991296..2f14948d 100644 --- a/nn_meter/kernel_detector/detection/detector.py +++ b/nn_meter/kernel_detector/kernel_detector.py @@ -1,11 +1,10 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.kernel_detector.rulelib.rule_reader import RuleReader -from nn_meter.kernel_detector.rulelib.rule_splitter import RuleSplitter from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kernel_detector.utils.constants import DUMMY_TYPES -from nn_meter.kernel_detector.utils.ir_tools import convert_nodes -# import logging +from .utils.constants import DUMMY_TYPES +from .utils.ir_tools import convert_nodes +from .rulelib.rule_reader import RuleReader +from .rulelib.rule_splitter import RuleSplitter class KernelDetector: diff --git a/nn_meter/kernel_detector/rulelib/rule_reader.py b/nn_meter/kernel_detector/rulelib/rule_reader.py index 8bb54c0c..4e2fdfd0 100644 --- a/nn_meter/kernel_detector/rulelib/rule_reader.py +++ b/nn_meter/kernel_detector/rulelib/rule_reader.py @@ -1,8 +1,8 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. import json +from ..fusionlib import get_fusion_unit from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kernel_detector.fusionlib import get_fusion_unit class RuleReader: diff --git a/nn_meter/kernel_detector/rulelib/rule_splitter.py b/nn_meter/kernel_detector/rulelib/rule_splitter.py index dac4446a..084e5af4 100644 --- a/nn_meter/kernel_detector/rulelib/rule_splitter.py +++ b/nn_meter/kernel_detector/rulelib/rule_splitter.py @@ -1,9 +1,9 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. from .rule_reader import RuleReader +from ..utils.match_helper import MatchHelper +from ..utils.fusion_aware_graph import FusionAwareGraph from nn_meter.utils.graph_tool import ModelGraph -from nn_meter.kernel_detector.utils.match_helper import MatchHelper -from nn_meter.kernel_detector.utils.fusion_aware_graph import FusionAwareGraph class RuleSplitter: diff --git a/nn_meter/kernel_detector/utils/fusion_aware_graph.py b/nn_meter/kernel_detector/utils/fusion_aware_graph.py index fc6dd01e..ab75f6e0 100644 --- a/nn_meter/kernel_detector/utils/fusion_aware_graph.py +++ b/nn_meter/kernel_detector/utils/fusion_aware_graph.py @@ -1,8 +1,8 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from nn_meter.utils.graph_tool import ModelGraph -from .union_find import UF import networkx as nx +from .union_find import UF +from nn_meter.utils.graph_tool import ModelGraph class FusionAwareGraph: diff --git a/nn_meter/nn_meter_cli.py b/nn_meter/nn_meter_cli.py index 55dccd27..39ce781a 100644 --- a/nn_meter/nn_meter_cli.py +++ b/nn_meter/nn_meter_cli.py @@ -5,12 +5,7 @@ import sys import argparse import logging -from nn_meter.nn_meter import * - -__user_config_folder__ = os.path.expanduser('~/.nn_meter/config') -__user_data_folder__ = os.path.expanduser('~/.nn_meter/data') - -__predictors_cfg_filename__ = 'predictors.yaml' +from nn_meter import * def list_latency_predictors_cli(): @@ -62,6 +57,7 @@ def apply_latency_predictor_cli(args): return result + def get_nnmeter_ir_cli(args): """convert pb file or onnx file to nn-Meter IR graph according to the command line interface arguments """ diff --git a/nn_meter/predictor/__init__.py b/nn_meter/predictor/__init__.py index 6bb62174..0f9eeef7 100644 --- a/nn_meter/predictor/__init__.py +++ b/nn_meter/predictor/__init__.py @@ -1,5 +1,4 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from .predictors.utils import latency_metrics - - +from .prediction.utils import latency_metrics +from .nn_meter_predictor import nnMeterPredictor, list_latency_predictors, load_latency_predictor diff --git a/nn_meter/predictor/nn_meter_predictor.py b/nn_meter/predictor/nn_meter_predictor.py index 0cdc99b0..aed99e2b 100644 --- a/nn_meter/predictor/nn_meter_predictor.py +++ b/nn_meter/predictor/nn_meter_predictor.py @@ -1,18 +1,18 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from glob import glob -from nn_meter.predictor.predictors.predict_by_kernel import nn_predict -from nn_meter.kernel_detector import KernelDetector -from nn_meter.ir_converter import model_file_to_graph, model_to_graph -from .utils import loading_to_local - -import yaml import os +import yaml import pkg_resources from shutil import copyfile from packaging import version import logging + +from .utils import loading_to_local +from .prediction.predict_by_kernel import nn_predict +from nn_meter.kernel_detector import KernelDetector from nn_meter.utils import load_config_file, get_user_data_folder +from nn_meter.ir_converter import model_file_to_graph, model_to_graph + __predictors_cfg_filename__ = 'predictors.yaml' diff --git a/nn_meter/predictor/predictors/__init__.py b/nn_meter/predictor/prediction/__init__.py similarity index 100% rename from nn_meter/predictor/predictors/__init__.py rename to nn_meter/predictor/prediction/__init__.py diff --git a/nn_meter/predictor/predictors/extract_feature.py b/nn_meter/predictor/prediction/extract_feature.py similarity index 100% rename from nn_meter/predictor/predictors/extract_feature.py rename to nn_meter/predictor/prediction/extract_feature.py index 1c2a91df..8a37c76c 100644 --- a/nn_meter/predictor/predictors/extract_feature.py +++ b/nn_meter/predictor/prediction/extract_feature.py @@ -1,8 +1,8 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. +import logging import numpy as np from sklearn.metrics import mean_squared_error -import logging def get_flop(input_channel, output_channel, k, H, W, stride): diff --git a/nn_meter/predictor/predictors/kernel_predictor.py b/nn_meter/predictor/prediction/kernel_predictor.py similarity index 100% rename from nn_meter/predictor/predictors/kernel_predictor.py rename to nn_meter/predictor/prediction/kernel_predictor.py diff --git a/nn_meter/predictor/predictors/predict_by_kernel.py b/nn_meter/predictor/prediction/predict_by_kernel.py similarity index 100% rename from nn_meter/predictor/predictors/predict_by_kernel.py rename to nn_meter/predictor/prediction/predict_by_kernel.py diff --git a/nn_meter/predictor/predictors/utils.py b/nn_meter/predictor/prediction/utils.py similarity index 99% rename from nn_meter/predictor/predictors/utils.py rename to nn_meter/predictor/prediction/utils.py index 2cf40a7a..3ffe1814 100644 --- a/nn_meter/predictor/predictors/utils.py +++ b/nn_meter/predictor/prediction/utils.py @@ -1,9 +1,9 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. - import numpy as np from sklearn.metrics import mean_squared_error + def get_kernel_name(optype): """ for many similar kernels, we use one kernel predictor since their latency difference is negligible, @@ -34,6 +34,7 @@ def get_kernel_name(optype): return optype + def get_accuracy(y_pred, y_true, threshold=0.01): a = (y_true - y_pred) / y_true b = np.where(abs(a) <= threshold) diff --git a/nn_meter/predictor/utils.py b/nn_meter/predictor/utils.py index add48c2b..cf5f5801 100644 --- a/nn_meter/predictor/utils.py +++ b/nn_meter/predictor/utils.py @@ -7,7 +7,7 @@ from tqdm import tqdm import requests import logging -from nn_meter.utils.utils import download_from_url +from nn_meter.utils import download_from_url def loading_to_local(pred_info, dir="data/predictorzoo"): diff --git a/nn_meter/utils/__init__.py b/nn_meter/utils/__init__.py index b8d46620..a27d1e9d 100644 --- a/nn_meter/utils/__init__.py +++ b/nn_meter/utils/__init__.py @@ -5,4 +5,5 @@ get_user_data_folder, change_user_data_folder, load_config_file -) \ No newline at end of file +) +from utils import download_from_url \ No newline at end of file diff --git a/nn_meter/utils/config_manager.py b/nn_meter/utils/config_manager.py index d1ca03d5..f8ace2a2 100644 --- a/nn_meter/utils/config_manager.py +++ b/nn_meter/utils/config_manager.py @@ -1,14 +1,9 @@ -from glob import glob -from nn_meter.predictor.predictors.predict_by_kernel import nn_predict -from nn_meter.kernel_detector import KernelDetector -from nn_meter.ir_converter import model_file_to_graph, model_to_graph -from nn_meter.predictor.load_predictors import loading_to_local - import yaml import os +import logging import pkg_resources from shutil import copyfile -import logging + __user_config_folder__ = os.path.expanduser('~/.nn_meter/config') __default_user_data_folder__ = os.path.expanduser('~/.nn_meter/data') diff --git a/nn_meter/utils/import_package.py b/nn_meter/utils/import_package.py index f41def33..08a5cb79 100644 --- a/nn_meter/utils/import_package.py +++ b/nn_meter/utils/import_package.py @@ -1,7 +1,7 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from packaging import version import logging +from packaging import version def try_import_onnx(require_version = ["1.9.0"]): diff --git a/nn_meter/utils/utils.py b/nn_meter/utils/utils.py index c7e7649e..02cd9191 100644 --- a/nn_meter/utils/utils.py +++ b/nn_meter/utils/utils.py @@ -20,7 +20,7 @@ def download_from_url(urladdr, ppath): if not os.path.isdir(ppath): os.makedirs(ppath) - # logging.keyinfo(f'Download from {urladdr}') + logging.keyinfo(f'Download from {urladdr}') response = requests.get(urladdr, stream=True) total_size_in_bytes = int(response.headers.get("content-length", 0)) block_size = 2048 # 2 Kibibyte From 5530cc5bc5203f0a23aa4aaf07d43127240aa32c Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 10:48:26 +0800 Subject: [PATCH 03/18] refine setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 46d98862..487a2789 100644 --- a/setup.py +++ b/setup.py @@ -26,7 +26,7 @@ ], packages=find_packages(), package_data={ - 'nn_meter': ['configs/*.yaml', 'kernel_detector/fusionlib/*.json'], + 'nn_meter': ['configs/*.yaml', 'nn-Meter/nn_meter/kernel_detector/fusionlib/*.json'], }, entry_points={ 'console_scripts': ['nn-meter=nn_meter.nn_meter_cli:nn_meter_cli'], From 5e22c26b30ccd7ec1a25689a5dc3f2316a318115 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 11:08:59 +0800 Subject: [PATCH 04/18] change lat_pred to predict --- README.md | 8 ++++---- docs/input_models.md | 14 +++++++------- docs/predictor/usage.md | 8 ++++---- nn_meter/nn_meter_cli.py | 2 +- tests/integration_test.py | 2 +- tests/integration_test_torch.py | 2 +- 6 files changed, 18 insertions(+), 18 deletions(-) diff --git a/README.md b/README.md index e4bcf34f..68e39172 100644 --- a/README.md +++ b/README.md @@ -98,16 +98,16 @@ After installation, a command named `nn-meter` is enabled. To predict the latenc ```bash # for Tensorflow (*.pb) file -nn-meter lat_pred --predictor [--predictor-version ] --tensorflow +nn-meter predict --predictor [--predictor-version ] --tensorflow # for ONNX (*.onnx) file -nn-meter lat_pred --predictor [--predictor-version ] --onnx +nn-meter predict --predictor [--predictor-version ] --onnx # for torch model from torchvision model zoo (str) -nn-meter lat_pred --predictor [--predictor-version ] --torchvision ... +nn-meter predict --predictor [--predictor-version ] --torchvision ... # for nn-Meter IR (*.json) file -nn-meter lat_pred --predictor [--predictor-version ] --nn-meter-ir +nn-meter predict --predictor [--predictor-version ] --nn-meter-ir ``` `--predictor-version ` arguments is optional. When the predictor version is not specified by users, nn-meter will use the latest version of the predictor. diff --git a/docs/input_models.md b/docs/input_models.md index 5424616d..50f98340 100644 --- a/docs/input_models.md +++ b/docs/input_models.md @@ -10,17 +10,17 @@ You can save tensorflow models into frozen pb formats, and use the following nn- ```bash # for Tensorflow (*.pb) file -nn-meter --predictor --tensorflow +nn-meter predict --predictor [--predictor-version ] --tensorflow ``` For the other frameworks (e.g., PyTorch), you can convert the models into onnx models, and use the following nn-meter command to predict the latency: ```bash # for ONNX (*.onnx) file -nn-meter --predictor --onnx +nn-meter predict --predictor [--predictor-version ] --onnx ``` -You can download the test [tensorflow models]("https://github.com/Lynazhang/nnmeter/releases/download/0.1/pb_models.zip") and [onnx models](https://github.com/Lynazhang/nnmeter/releases/download/0.1/onnx_models.zip). +You can download the test [tensorflow models]("https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/pb_models.zip") and [onnx models](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/onnx_models.zip). ### Input model as a code object @@ -29,7 +29,7 @@ You can also directly apply nn-Meter in your python code. In this case, please d ```python from nn_meter import load_latency_predictor -predictor = load_lat_predictor(hardware_name) # case insensitive in backend +predictor = load_latency_predictor(hardware_name) # case insensitive in backend # build your model here model = ... # model is instance of torch.nn.Module @@ -57,14 +57,14 @@ For a *node*, we use the identical node name ("conv1.conv/Conv2D") as the node k * outbounds: a list of outgoing node names. The inbounds and outbounds describe the node connections. * attr: a set of attributes for the node. The attributes can be different for different types of NN node. -You can download the example nn-Meter IR graphs through [here](https://github.com/Lynazhang/nnmeter/releases/download/0.1/ir_graphs.zip). +You can download the example nn-Meter IR graphs through [here](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/ir_graphs.zip). When you have a large amount of models to predict, you can also convert them into nn-Meter IR graphs to save the pre-processing time: ``` # for Tensorflow (*.pb) file -nn-meter getir --tensorflow --output +nn-meter get_ir --tensorflow [--output ] # for ONNX (*.onnx) file -nn-meter getir --onnx --output +nn-meter get_ir --onnx [--output ] ``` diff --git a/docs/predictor/usage.md b/docs/predictor/usage.md index 4b6fad7e..6d30f29b 100644 --- a/docs/predictor/usage.md +++ b/docs/predictor/usage.md @@ -36,16 +36,16 @@ After installation, a command named `nn-meter` is enabled. To predict the latenc ```bash # for Tensorflow (*.pb) file -nn-meter lat_pred --predictor [--predictor-version ] --tensorflow +nn-meter predict --predictor [--predictor-version ] --tensorflow # for ONNX (*.onnx) file -nn-meter lat_pred --predictor [--predictor-version ] --onnx +nn-meter predict --predictor [--predictor-version ] --onnx # for torch model from torchvision model zoo (str) -nn-meter lat_pred --predictor [--predictor-version ] --torchvision ... +nn-meter predict --predictor [--predictor-version ] --torchvision ... # for nn-Meter IR (*.json) file -nn-meter lat_pred --predictor [--predictor-version ] --nn-meter-ir +nn-meter predict --predictor [--predictor-version ] --nn-meter-ir ``` `--predictor-version ` arguments is optional. When the predictor version is not specified by users, nn-meter will use the latest version of the predictor. diff --git a/nn_meter/nn_meter_cli.py b/nn_meter/nn_meter_cli.py index 39ce781a..93bce6cf 100644 --- a/nn_meter/nn_meter_cli.py +++ b/nn_meter/nn_meter_cli.py @@ -113,7 +113,7 @@ def nn_meter_cli(): subparsers = parser.add_subparsers() # Usage 1: latency predictors - lat_pred = subparsers.add_parser('lat_pred', help='apply latency predictor for testing model') + lat_pred = subparsers.add_parser('predict', help='apply latency predictor for testing model') lat_pred.add_argument( "--predictor", type=str, diff --git a/tests/integration_test.py b/tests/integration_test.py index eb2371a3..b20f2ad9 100644 --- a/tests/integration_test.py +++ b/tests/integration_test.py @@ -82,7 +82,7 @@ def integration_test(model_type, url, ppath, output_name = "tests/test_result.tx try: since = time.time() # print(f'nn-meter --{model_type} {ppath} --predictor {pred_name} --predictor-version {pred_version}') - result = subprocess.check_output(['nn-meter', 'lat_pred', f'--{model_type}', f'{ppath}', '--predictor', f'{pred_name}', '--predictor-version', f'{pred_version}']) + result = subprocess.check_output(['nn-meter', 'predict', f'--{model_type}', f'{ppath}', '--predictor', f'{pred_name}', '--predictor-version', f'{pred_version}']) runtime = time.time() - since except NotImplementedError: logging.error(f"Meets ERROR when checking --{model_type} {ppath} --predictor {pred_name} --predictor-version {pred_version}") diff --git a/tests/integration_test_torch.py b/tests/integration_test_torch.py index 6dbef468..482d9b99 100644 --- a/tests/integration_test_torch.py +++ b/tests/integration_test_torch.py @@ -43,7 +43,7 @@ def integration_test_onnx_based_torch(model_type, model_list, output_name = "tes try: since = time.time() # print(f'nn-meter --torchvision ' + " ".join(model_list) + f' --predictor {pred_name} --predictor-version {pred_version}') - result = subprocess.check_output(['nn-meter', 'lat_pred', f'--torchvision'] + model_list + ['--predictor', f'{pred_name}', '--predictor-version', f'{pred_version}']) + result = subprocess.check_output(['nn-meter', 'predict', f'--torchvision'] + model_list + ['--predictor', f'{pred_name}', '--predictor-version', f'{pred_version}']) runtime = time.time() - since except NotImplementedError: logging.error("Meets ERROR when checking --torchvision {model_list} --predictor {pred_name} --predictor-version {pred_version}") From bc61d73a4f015e0c89703201bd44e97d439ec99f Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 11:12:00 +0800 Subject: [PATCH 05/18] fix typo --- nn_meter/utils/__init__.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/nn_meter/utils/__init__.py b/nn_meter/utils/__init__.py index a27d1e9d..7c5eb826 100644 --- a/nn_meter/utils/__init__.py +++ b/nn_meter/utils/__init__.py @@ -1,9 +1,9 @@ # Copyright (c) Microsoft Corporation. # Licensed under the MIT license. -from config_manager import ( +from .config_manager import ( create_user_configs, get_user_data_folder, change_user_data_folder, load_config_file ) -from utils import download_from_url \ No newline at end of file +from .utils import download_from_url \ No newline at end of file From f71829f0620d17d0513a8352ac52f5582da5867a Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 11:18:09 +0800 Subject: [PATCH 06/18] fix typo --- nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py b/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py index fc8caec4..a2f2025a 100644 --- a/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py +++ b/nn_meter/ir_converter/frozenpb_converter/shape_fetcher.py @@ -2,7 +2,7 @@ # Licensed under the MIT license. import numpy as np from typing import List -from nn_meter.utils.utils import try_import_tensorflow +from nn_meter.utils.import_package import try_import_tensorflow class ShapeFetcher: def __init__(self, input_graph): From 5aa8d60b53d8554e05d4077ab72c875e76d4ecf8 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 12:46:51 +0800 Subject: [PATCH 07/18] refine setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 487a2789..46d98862 100644 --- a/setup.py +++ b/setup.py @@ -26,7 +26,7 @@ ], packages=find_packages(), package_data={ - 'nn_meter': ['configs/*.yaml', 'nn-Meter/nn_meter/kernel_detector/fusionlib/*.json'], + 'nn_meter': ['configs/*.yaml', 'kernel_detector/fusionlib/*.json'], }, entry_points={ 'console_scripts': ['nn-meter=nn_meter.nn_meter_cli:nn_meter_cli'], From efbe102f7c062978ad8e56d8e92845b8557f6880 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 12:53:29 +0800 Subject: [PATCH 08/18] add alias for prev version of lat_pred --- nn_meter/nn_meter_cli.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nn_meter/nn_meter_cli.py b/nn_meter/nn_meter_cli.py index 93bce6cf..36bfe7dd 100644 --- a/nn_meter/nn_meter_cli.py +++ b/nn_meter/nn_meter_cli.py @@ -113,7 +113,7 @@ def nn_meter_cli(): subparsers = parser.add_subparsers() # Usage 1: latency predictors - lat_pred = subparsers.add_parser('predict', help='apply latency predictor for testing model') + lat_pred = subparsers.add_parser('predict', aliases=['lat_pred'], help='apply latency predictor for testing model') lat_pred.add_argument( "--predictor", type=str, From 421efa0d67670bf9d1dec9c28ad9ca730de3d168 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Thu, 4 Nov 2021 13:52:23 +0800 Subject: [PATCH 09/18] fix package change typo --- nn_meter/utils/config_manager.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/nn_meter/utils/config_manager.py b/nn_meter/utils/config_manager.py index f8ace2a2..ad7218c3 100644 --- a/nn_meter/utils/config_manager.py +++ b/nn_meter/utils/config_manager.py @@ -15,9 +15,11 @@ def create_user_configs(): """create user configs from distributed configs """ os.makedirs(__user_config_folder__, exist_ok=True) - # TODO/backlog: to handle config merging when upgrading - for f in pkg_resources.resource_listdir(__name__, 'configs'): - copyfile(pkg_resources.resource_filename(__name__, f'configs/{f}'), os.path.join(__user_config_folder__, f)) + # TODO/backlog: to handle config merging when upgrading + for f in pkg_resources.resource_listdir(".".join(__name__.split('.')[:-2]), 'configs'): + copyfile( + pkg_resources.resource_filename(".".join(__name__.split('.')[:-2]), f'configs/{f}'), + os.path.join(__user_config_folder__, f)) # make default setting yaml file with open(os.path.join(__user_config_folder__, 'settings.yaml'), 'w') as fp: yaml.dump({'data_folder': __default_user_data_folder__}, fp) From 06c5a9c3ba2ea374d806df55d51224c7e8f3974e Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Mon, 8 Nov 2021 16:56:58 +0800 Subject: [PATCH 10/18] refine md reference link --- docs/overview.md | 4 ++-- docs/predictor/hardware-aware-model-design.md | 2 +- docs/predictor/usage.md | 6 +++--- docs/quick_start.md | 4 ++-- tests/README.md | 4 ++-- 5 files changed, 10 insertions(+), 10 deletions(-) diff --git a/docs/overview.md b/docs/overview.md index 36a01af6..22d7197f 100644 --- a/docs/overview.md +++ b/docs/overview.md @@ -19,6 +19,6 @@ If you have a new hardware to predict DNN latency, a re-run of nn-Meter is requ ## Learn More - [Get started](quick_start.md) -- [How to use nn-Meter](usage.md) +- [How to use nn-Meter Predictor](predictor/usage.md) -- [nn-meter in hardware-aware NAS](hardware-aware-model-design.md) \ No newline at end of file +- [nn-meter in hardware-aware NAS](predictor/hardware-aware-model-design.md) \ No newline at end of file diff --git a/docs/predictor/hardware-aware-model-design.md b/docs/predictor/hardware-aware-model-design.md index efcfbcd6..8bd69a60 100644 --- a/docs/predictor/hardware-aware-model-design.md +++ b/docs/predictor/hardware-aware-model-design.md @@ -16,7 +16,7 @@ Next, we introduce our hardware-aware NAS framework[[1]](https://openaccess.thec Our HW-NAS framework firstly automatically selects the hardware-friendly operators (or blocks) by considering both representation capacity and hardware efficiency. The selected operators could establish a ***hardware-aware search space*** for most of existing NAS algorithms. -**Latency Prediction in search process by nn-Meter.** Different with other simple predictors (e.g., look-up table for operators/blocks, linear regression models), [nn-Meter](overview.md) conducts kernel-level prediction, which captures the complex model graph optimizations on edge devices. nn-Meter is the first accurate latency prediction tool for DNNs on edge devices. +**Latency Prediction in search process by nn-Meter.** Different with other simple predictors (e.g., look-up table for operators/blocks, linear regression models), [nn-Meter](../overview.md) conducts kernel-level prediction, which captures the complex model graph optimizations on edge devices. nn-Meter is the first accurate latency prediction tool for DNNs on edge devices. Besides the search space specialization, our HW-NAS framework also allows combining nn-Meter with existing NAS algorithms in the optimization objectives and constraints. As described in [[4]](http://arxiv.org/abs/2101.09336), the HW-NAS algorithms often consider hardware efficiency metrics as the constraints of existing NAS formulation or part of the scalarized loss functions (e.g., the loss is weighted sum of both cross entropy loss and hardware-aware penalty). Since the NAS process may sample up to millions of candidate model architectures, the obtaining of hardware metrics must be accurate and efficient. diff --git a/docs/predictor/usage.md b/docs/predictor/usage.md index 6d30f29b..def7e76d 100644 --- a/docs/predictor/usage.md +++ b/docs/predictor/usage.md @@ -1,8 +1,8 @@ -# Usage +# Usage of nn-Meter Predictor To apply for hardware latency prediction, nn-Meter provides two types of interfaces： -- command line `nn-meter` after `nn-meter` [installation](QuickStart.md#Installation). +- command line `nn-meter` after `nn-meter` [installation](../quick_start.md#Installation). - Python binding provided by the module `nn_meter` Here is a summary of supported inputs of the two methods. @@ -12,7 +12,7 @@ Here is a summary of supported inputs of the two methods. | Tensorflow | Checkpoint file dumped by `tf.saved_model()` and end with `.pb` | Checkpoint file dumped by `tf.saved_model` and end with `.pb` | | Torch | Models in `torchvision.models` | Object of `torch.nn.Module` | | Onnx | Checkpoint file dumped by `onnx.save()` and end with `.onnx` | Checkpoint file dumped by `onnx.save()` or model loaded by `onnx.load()` | -| nn-Meter IR graph | Json file in the format of [nn-Meter IR Graph](input_models.md#nnmeter-ir-graph) | `dict` object following the format of [nn-Meter IR Graph](input_models.md#nnmeter-ir-graph) | +| nn-Meter IR graph | Json file in the format of [nn-Meter IR Graph](../input_models.md#nnmeter-ir-graph) | `dict` object following the format of [nn-Meter IR Graph](../input_models.md#nnmeter-ir-graph) | | NNI IR graph | - | NNI IR graph object | In both methods, users could appoint predictor name and version to target a specific hardware platform (device). Currently, nn-Meter supports prediction on the following four configs: diff --git a/docs/quick_start.md b/docs/quick_start.md index ff18206f..baaf6630 100644 --- a/docs/quick_start.md +++ b/docs/quick_start.md @@ -28,7 +28,7 @@ nn-Meter is a latency predictor of models with type of Tensorflow, PyTorch, Onnx | nn-Meter IR graph | --- | | NNI IR graph | `nni>=2.4` | -[1] Please refer to [nn-Meter Usage](usage.md#torch-model-converters) for more information. +[1] Please refer to [nn-Meter Usage](predictor/usage.md#torch-model-converters) for more information. Please also check the versions of `numpy` and `scikit_learn`. The different versions may change the prediction accuracy of kernel predictors. @@ -59,4 +59,4 @@ if __name__ == '__main__': main() ``` -For more detailed usage of nn-Meter, please refer to [this doc](usage.md). +For more detailed usage of nn-Meter, please refer to [this doc](predictor/usage.md). diff --git a/tests/README.md b/tests/README.md index e97e8109..88c8df7b 100644 --- a/tests/README.md +++ b/tests/README.md @@ -2,9 +2,9 @@ In nn-Meter/tests, we implement the integration test for all usages of nn-Meter. ## Integration test -According to [nn-Meter usage](nn-Meter/docs/usage.md), nn-Meter is a latency predictor of models with type of Tensorflow, PyTorch, Onnx, nn-meter IR graph and NNI IR graph. In integration test, we run the test for mentioned models, collect the latency results, and compare the results with the reference results. For time saving and readability, we separate the integration test into two scripts with PyTorch model and others, respectively. +According to [nn-Meter usage](../docs/predictor/usage.md), nn-Meter is a latency predictor of models with type of Tensorflow, PyTorch, Onnx, nn-meter IR graph and NNI IR graph. In integration test, we run the test for mentioned models, collect the latency results, and compare the results with the reference results. For time saving and readability, we separate the integration test into two scripts with PyTorch model and others, respectively. -For PyTorch model, we accomplished two graph converters, namely NNI-based torch converter and ONNX-based torch converter (Refer to [this doc](docs/usage.md#torch-model-converters) for more information). We test both converters in `tests/integration_test_torch.py`. Note that the NNI-based torch converter needs API from `nni.retiarii.nn.pytorch` (view [NNI doc](https://nni.readthedocs.io/en/stable/NAS/QuickStart.html#define-base-model)) to build the torch module, thus we collected torchvision models and modified the import package to meet NNI requirements. The modified model are saved in tests/torchmodels. +For PyTorch model, we accomplished two graph converters, namely NNI-based torch converter and ONNX-based torch converter (Refer to [this doc](../docs/predictor/usage.md#torch-model-converters) for more information). We test both converters in `tests/integration_test_torch.py`. Note that the NNI-based torch converter needs API from `nni.retiarii.nn.pytorch` (view [NNI doc](https://nni.readthedocs.io/en/stable/NAS/QuickStart.html#define-base-model)) to build the torch module, thus we collected torchvision models and modified the import package to meet NNI requirements. The modified model are saved in tests/torchmodels. ## github actions workflow From 81e56ac0c7b2ceeaf671cbafd8d80fbd3dcf0624 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 14:58:25 +0800 Subject: [PATCH 11/18] rename requirments --- docs/requirements/{requirements => requirements.txt} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/requirements/{requirements => requirements.txt} (100%) diff --git a/docs/requirements/requirements b/docs/requirements/requirements.txt similarity index 100% rename from docs/requirements/requirements rename to docs/requirements/requirements.txt From f490f3b6814d9b4db30598ff80714faf5c584d6c Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 15:20:23 +0800 Subject: [PATCH 12/18] refine example name --- examples/README.md | 18 +- ...t.ipynb => nn-meter_dataset_for_gnn.ipynb} | 240 +++++++++--------- ...n-meter_predictor_for_bench_dataset.ipynb} | 0 ...redictor_for_different_model_format.ipynb} | 0 4 files changed, 129 insertions(+), 129 deletions(-) rename examples/{gnn_for_bench_dataset.ipynb => nn-meter_dataset_for_gnn.ipynb} (67%) rename examples/{nn-meter_for_bench_dataset.ipynb => nn-meter_predictor_for_bench_dataset.ipynb} (100%) rename examples/{nn-meter_for_different_model_format.ipynb => nn-meter_predictor_for_different_model_format.ipynb} (100%) diff --git a/examples/README.md b/examples/README.md index 41599e76..3baf52b7 100644 --- a/examples/README.md +++ b/examples/README.md @@ -2,7 +2,7 @@ In this folder, we provide several examples to show the usage of nn-Meter package. -The first example [1. Use nn-Meter for models with different format](nn-meter_for_different_model_format.ipynb) shows the basic python binding usage of nn-meter with models with different format of Tensorflow, PyTorch and ONNX model. +The first example [1. Use nn-Meter Predictor for models with different format](nn-meter_predictor_for_different_model_format.ipynb) shows the basic python binding usage of nn-meter with models with different format of Tensorflow, PyTorch and ONNX model. #### Benchmark dataset @@ -10,18 +10,18 @@ To evaluate the effectiveness of a prediction model on an arbitrary DNN model, w We release the dataset, and provide an interface of `nn_meter.dataset` for users to get access to the dataset. Users can also download the data from the [Download Link](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip) on their own. -Example [2. Use nn-Meter with the bench dataset](nn-meter_for_bench_dataset.ipynb) shows how to use nn-Meter to predict latency for the bench dataset. +Example [2. Use nn-Meter with the bench dataset](nn-meter_predictor_for_bench_dataset.ipynb) shows how to use nn-Meter to predict latency for the bench dataset. -Since the dataset is encoded in a graph format, we also provide an example [3. Use bench dataset for GNN training](gnn_for_bench_dataset.ipynb) of using GCN to predict the model latency with the bench dataset. +Since the dataset is encoded in a graph format, we also provide an example [3. Use nn-Meter bench dataset for GNN training](nn-meter_dataset_for_gnn.ipynb) of using GCN to predict the model latency with the bench dataset. Finally, we provide more hardware-ware NAS examples in NNI. ## Examples list -1. [Use nn-Meter for models with different format](nn-meter_for_different_model_format.ipynb) -2. [Use nn-Meter with the bench dataset](nn-meter_for_bench_dataset.ipynb) -3. [Use bench dataset for GNN training](gnn_for_bench_dataset.ipynb) -4. Use nn-Meter to construct latency constraint in SPOS NAS (TBD) +1. [Use nn-Meter for models with different format](nn-meter_predictor_for_different_model_format.ipynb) +2. [Use nn-Meter with the bench dataset](nn-meter_predictor_for_bench_dataset.ipynb) +3. [Use bench dataset for GNN training](nn-meter_dataset_for_gnn.ipynb) +4. Use nn-Meter to construct latency constraint in SPOS NAS - [Use nn-Meter in search part](https://github.com/microsoft/nni/blob/master/examples/nas/oneshot/spos/multi_trial.py) - - [Use nn-Meter in sampling part](https://github.com/microsoft/nni/blob/master/examples/nas/oneshot/spos/supernet.py) -5. [Use nn-Meter to construct latency penalty in Proxyless NAS](https://github.com/microsoft/nni/tree/master/examples/nas/oneshot/proxylessnas) + - [Use nn-Meter in sampling part (TBD)](https://github.com/microsoft/nni/blob/master/examples/nas/oneshot/spos/supernet.py) +5. [Use nn-Meter to construct latency penalty in ProxylessNAS](https://github.com/microsoft/nni/tree/master/examples/nas/oneshot/proxylessnas) diff --git a/examples/gnn_for_bench_dataset.ipynb b/examples/nn-meter_dataset_for_gnn.ipynb similarity index 67% rename from examples/gnn_for_bench_dataset.ipynb rename to examples/nn-meter_dataset_for_gnn.ipynb index db2f25cc..74ada8d4 100644 --- a/examples/gnn_for_bench_dataset.ipynb +++ b/examples/nn-meter_dataset_for_gnn.ipynb @@ -2,6 +2,7 @@ "cells": [ { "cell_type": "markdown", + "metadata": {}, "source": [ "# Latency Dataset - GNN Model\n", "\n", @@ -12,21 +13,30 @@ "To better deal with the problems above, we give a GNN example with graph representation improved. We first build our GNN model, which is constructed based on GraphSAGE, and maxpooling is selected as out pooling method. Next, we will start training after the data is loaded. `GNNDataset` and `GNNDataloader` in `nn_meter/dataset/gnn_dataloader.py` build the model structure of the Dataset in `.jsonl` format into our required Dataset and Dataloader. \n", "\n", "Let's start our journey!" - ], - "metadata": {} + ] }, { "cell_type": "markdown", + "metadata": {}, "source": [ "## Step 1: Build our GraphSAGE Model\n", "\n", "We built our model with the help of DGL library." - ], - "metadata": {} + ] }, { "cell_type": "code", "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Using backend: pytorch\n" + ] + } + ], "source": [ "import torch\n", "import torch.nn as nn\n", @@ -72,52 +82,25 @@ " x = self.pooling(g, x)\n", " x = self.fc1(x)\n", " return self.fc(x)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stderr", - "text": [ - "Using backend: pytorch\n" - ] - } - ], - "metadata": {} + ] }, { "cell_type": "markdown", + "metadata": {}, "source": [ "## Step 2: Loading Data.\n", "\n", "Next, we will finish loading the data and learn about the size of the Training and Testing datasets." - ], - "metadata": {} + ] }, { "cell_type": "code", "execution_count": 2, - "source": [ - "import os\r\n", - "from nn_meter.dataset import gnn_dataloader\r\n", - "\r\n", - "target_device = \"cortexA76cpu_tflite21\"\r\n", - "\r\n", - "print(\"Processing Training Set.\")\r\n", - "train_set = gnn_dataloader.GNNDataset(train=True, device=target_device) \r\n", - "print(\"Processing Testing Set.\")\r\n", - "test_set = gnn_dataloader.GNNDataset(train=False, device=target_device)\r\n", - "\r\n", - "train_loader = gnn_dataloader.GNNDataloader(train_set, batchsize=1 , shuffle=True)\r\n", - "test_loader = gnn_dataloader.GNNDataloader(test_set, batchsize=1, shuffle=False)\r\n", - "print('Train Dataset Size:', len(train_set))\r\n", - "print('Testing Dataset Size:', len(test_set))\r\n", - "print('Attribute tensor shape:', next(train_loader)[1].ndata['h'].size(1))\r\n", - "ATTR_COUNT = next(train_loader)[1].ndata['h'].size(1)" - ], + "metadata": {}, "outputs": [ { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Processing Training Set.\n", "Processing Testing Set.\n", @@ -127,101 +110,42 @@ ] } ], - "metadata": {} + "source": [ + "import os\n", + "from nn_meter.dataset import gnn_dataloader\n", + "\n", + "target_device = \"cortexA76cpu_tflite21\"\n", + "\n", + "print(\"Processing Training Set.\")\n", + "train_set = gnn_dataloader.GNNDataset(train=True, device=target_device) \n", + "print(\"Processing Testing Set.\")\n", + "test_set = gnn_dataloader.GNNDataset(train=False, device=target_device)\n", + "\n", + "train_loader = gnn_dataloader.GNNDataloader(train_set, batchsize=1 , shuffle=True)\n", + "test_loader = gnn_dataloader.GNNDataloader(test_set, batchsize=1, shuffle=False)\n", + "print('Train Dataset Size:', len(train_set))\n", + "print('Testing Dataset Size:', len(test_set))\n", + "print('Attribute tensor shape:', next(train_loader)[1].ndata['h'].size(1))\n", + "ATTR_COUNT = next(train_loader)[1].ndata['h'].size(1)" + ] }, { "cell_type": "markdown", + "metadata": {}, "source": [ "## Step 3: Run and Test\n", "\n", "We can run the model and evaluate it now!" - ], - "metadata": {} + ] }, { "cell_type": "code", "execution_count": 3, - "source": [ - "if torch.cuda.is_available():\r\n", - " print(\"Using CUDA.\")\r\n", - "# device = \"cpu\"\r\n", - "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\r\n", - "\r\n", - "# Start Training\r\n", - "load_model = False\r\n", - "if load_model:\r\n", - " model = GNN(ATTR_COUNT, 3, 400, 0.1).to(device)\r\n", - " opt = torch.optim.AdamW(model.parameters(), lr=4e-4)\r\n", - " checkpoint = torch.load('LatencyGNN.pt')\r\n", - " model.load_state_dict(checkpoint['model_state_dict'])\r\n", - " opt.load_state_dict(checkpoint['optimizer_state_dict'])\r\n", - " # EPOCHS = checkpoint['epoch']\r\n", - " EPOCHS = 0\r\n", - " loss_func = checkpoint['loss']\r\n", - "else:\r\n", - " model = GNN(ATTR_COUNT, 3, 400, 0.1).to(device)\r\n", - " opt = torch.optim.AdamW(model.parameters(), lr=4e-4)\r\n", - " EPOCHS=20\r\n", - " loss_func = nn.L1Loss()\r\n", - "\r\n", - "lr_scheduler = CosineAnnealingLR(opt, T_max=EPOCHS)\r\n", - "loss_sum = 0\r\n", - "for epoch in range(EPOCHS):\r\n", - " train_length = len(train_set)\r\n", - " tran_acc_ten = 0\r\n", - " loss_sum = 0 \r\n", - " # latency, graph, types, flops\r\n", - " for batched_l, batched_g in train_loader:\r\n", - " opt.zero_grad()\r\n", - " batched_l = batched_l.to(device).float()\r\n", - " batched_g = batched_g.to(device)\r\n", - " batched_f = batched_g.ndata['h'].float()\r\n", - " logits = model(batched_g, batched_f)\r\n", - " for i in range(len(batched_l)):\r\n", - " pred_latency = logits[i].item()\r\n", - " prec_latency = batched_l[i].item()\r\n", - " if (pred_latency >= 0.9 * prec_latency) and (pred_latency <= 1.1 * prec_latency):\r\n", - " tran_acc_ten += 1\r\n", - " # print(\"true latency: \", batched_l)\r\n", - " # print(\"Predict latency: \", logits)\r\n", - " batched_l = torch.reshape(batched_l, (-1 ,1))\r\n", - " loss = loss_func(logits, batched_l)\r\n", - " loss_sum += loss\r\n", - " loss.backward()\r\n", - " opt.step()\r\n", - " lr_scheduler.step()\r\n", - " print(\"[Epoch \", epoch, \"]: \", \"Training accuracy within 10%: \", tran_acc_ten / train_length * 100, \" %.\")\r\n", - " # print('Learning Rate:', lr_scheduler.get_last_lr())\r\n", - " # print('Loss:', loss_sum / train_length)\r\n", - "\r\n", - "# Save The Best Model\r\n", - "torch.save({\r\n", - " 'epoch': EPOCHS,\r\n", - " 'model_state_dict': model.state_dict(),\r\n", - " 'optimizer_state_dict': opt.state_dict(),\r\n", - " 'loss': loss_func,\r\n", - "}, 'LatencyGNN.pt')\r\n", - "\r\n", - "# Start Testing\r\n", - "count = 0\r\n", - "with torch.no_grad():\r\n", - " test_length = len(test_set)\r\n", - " test_acc_ten = 0\r\n", - " for batched_l, batched_g in test_loader:\r\n", - " batched_l = batched_l.to(device).float()\r\n", - " batched_g = batched_g.to(device)\r\n", - " batched_f = batched_g.ndata['h'].float()\r\n", - " result = model(batched_g, batched_f)\r\n", - " if (result.item() >= 0.9 * batched_l.item()) and (result.item() <= 1.1 * batched_l.item()):\r\n", - " test_acc_ten += 1\r\n", - " acc = (abs(result.item() - batched_l.item()) / batched_l.item()) * 100\r\n", - " count += 1\r\n", - " print(\"Testing accuracy within 10%: \", test_acc_ten / test_length * 100, \" %.\")" - ], + "metadata": {}, "outputs": [ { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "[Epoch 0 ]: Training accuracy within 10%: 21.999807061547365 %.\n", "[Epoch 1 ]: Training accuracy within 10%: 27.725255643449742 %.\n", @@ -247,7 +171,83 @@ ] } ], - "metadata": {} + "source": [ + "if torch.cuda.is_available():\n", + " print(\"Using CUDA.\")\n", + "# device = \"cpu\"\n", + "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n", + "\n", + "# Start Training\n", + "load_model = False\n", + "if load_model:\n", + " model = GNN(ATTR_COUNT, 3, 400, 0.1).to(device)\n", + " opt = torch.optim.AdamW(model.parameters(), lr=4e-4)\n", + " checkpoint = torch.load('LatencyGNN.pt')\n", + " model.load_state_dict(checkpoint['model_state_dict'])\n", + " opt.load_state_dict(checkpoint['optimizer_state_dict'])\n", + " # EPOCHS = checkpoint['epoch']\n", + " EPOCHS = 0\n", + " loss_func = checkpoint['loss']\n", + "else:\n", + " model = GNN(ATTR_COUNT, 3, 400, 0.1).to(device)\n", + " opt = torch.optim.AdamW(model.parameters(), lr=4e-4)\n", + " EPOCHS=20\n", + " loss_func = nn.L1Loss()\n", + "\n", + "lr_scheduler = CosineAnnealingLR(opt, T_max=EPOCHS)\n", + "loss_sum = 0\n", + "for epoch in range(EPOCHS):\n", + " train_length = len(train_set)\n", + " tran_acc_ten = 0\n", + " loss_sum = 0 \n", + " # latency, graph, types, flops\n", + " for batched_l, batched_g in train_loader:\n", + " opt.zero_grad()\n", + " batched_l = batched_l.to(device).float()\n", + " batched_g = batched_g.to(device)\n", + " batched_f = batched_g.ndata['h'].float()\n", + " logits = model(batched_g, batched_f)\n", + " for i in range(len(batched_l)):\n", + " pred_latency = logits[i].item()\n", + " prec_latency = batched_l[i].item()\n", + " if (pred_latency >= 0.9 * prec_latency) and (pred_latency <= 1.1 * prec_latency):\n", + " tran_acc_ten += 1\n", + " # print(\"true latency: \", batched_l)\n", + " # print(\"Predict latency: \", logits)\n", + " batched_l = torch.reshape(batched_l, (-1 ,1))\n", + " loss = loss_func(logits, batched_l)\n", + " loss_sum += loss\n", + " loss.backward()\n", + " opt.step()\n", + " lr_scheduler.step()\n", + " print(\"[Epoch \", epoch, \"]: \", \"Training accuracy within 10%: \", tran_acc_ten / train_length * 100, \" %.\")\n", + " # print('Learning Rate:', lr_scheduler.get_last_lr())\n", + " # print('Loss:', loss_sum / train_length)\n", + "\n", + "# Save The Best Model\n", + "torch.save({\n", + " 'epoch': EPOCHS,\n", + " 'model_state_dict': model.state_dict(),\n", + " 'optimizer_state_dict': opt.state_dict(),\n", + " 'loss': loss_func,\n", + "}, 'LatencyGNN.pt')\n", + "\n", + "# Start Testing\n", + "count = 0\n", + "with torch.no_grad():\n", + " test_length = len(test_set)\n", + " test_acc_ten = 0\n", + " for batched_l, batched_g in test_loader:\n", + " batched_l = batched_l.to(device).float()\n", + " batched_g = batched_g.to(device)\n", + " batched_f = batched_g.ndata['h'].float()\n", + " result = model(batched_g, batched_f)\n", + " if (result.item() >= 0.9 * batched_l.item()) and (result.item() <= 1.1 * batched_l.item()):\n", + " test_acc_ten += 1\n", + " acc = (abs(result.item() - batched_l.item()) / batched_l.item()) * 100\n", + " count += 1\n", + " print(\"Testing accuracy within 10%: \", test_acc_ten / test_length * 100, \" %.\")" + ] } ], "metadata": { @@ -269,9 +269,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.8" + "version": "3.6.10" } }, "nbformat": 4, "nbformat_minor": 2 -} \ No newline at end of file +} diff --git a/examples/nn-meter_for_bench_dataset.ipynb b/examples/nn-meter_predictor_for_bench_dataset.ipynb similarity index 100% rename from examples/nn-meter_for_bench_dataset.ipynb rename to examples/nn-meter_predictor_for_bench_dataset.ipynb diff --git a/examples/nn-meter_for_different_model_format.ipynb b/examples/nn-meter_predictor_for_different_model_format.ipynb similarity index 100% rename from examples/nn-meter_for_different_model_format.ipynb rename to examples/nn-meter_predictor_for_different_model_format.ipynb From ec3dc4e8dad05c99f821a7ee5ca86bbaa6946580 Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 15:41:27 +0800 Subject: [PATCH 13/18] add doc for bench dataset --- docs/dataset.md | 8 ++++++++ examples/README.md | 4 +--- 2 files changed, 9 insertions(+), 3 deletions(-) create mode 100644 docs/dataset.md diff --git a/docs/dataset.md b/docs/dataset.md new file mode 100644 index 00000000..674abf1a --- /dev/null +++ b/docs/dataset.md @@ -0,0 +1,8 @@ +# Benchmark dataset + +To evaluate the effectiveness of a prediction model on an arbitrary DNN model, we need a representative dataset that covers a large prediction scope. nn-Meter collects and generates 26k CNN models (Please refer the paper for the dataset generation method). + +We release the dataset, and provide an interface of `nn_meter.dataset` for users to get access to the dataset. This interface could automatically download the nn-Meter bench dataset and return the path of the dataset when calling. Users can also download the data from the [Download Link](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip) on their own. This [example](../examples/nn-meter_predictor_for_bench_dataset.ipynb) shows how to use nn-Meter predictor to predict latency for the bench dataset. + +Since the dataset is encoded in a graph format, we also provide an interface of `nn_meter.dataset.gnn_dataloader` for GNN training. By this interface, `GNNDataset` and `GNNDataloader` build the model structure of the bench dataset in `.jsonl` format into GNN required dataset and data loader. Users could refer to this [example](../examples/nn-meter_dataset_for_gnn.ipynb) for further information of `gnn_dataloader`. Note that to apply nn-Meter bench dataset for GNN training, the package `torch` and `dgl` should be installed. + diff --git a/examples/README.md b/examples/README.md index 3baf52b7..af15f6d4 100644 --- a/examples/README.md +++ b/examples/README.md @@ -4,15 +4,13 @@ In this folder, we provide several examples to show the usage of nn-Meter packag The first example [1. Use nn-Meter Predictor for models with different format](nn-meter_predictor_for_different_model_format.ipynb) shows the basic python binding usage of nn-meter with models with different format of Tensorflow, PyTorch and ONNX model. -#### Benchmark dataset - To evaluate the effectiveness of a prediction model on an arbitrary DNN model, we need a representative dataset that covers a large prediction scope. nn-Meter collects and generates 26k CNN models. (Please refer the paper for the dataset generation method.) We release the dataset, and provide an interface of `nn_meter.dataset` for users to get access to the dataset. Users can also download the data from the [Download Link](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip) on their own. Example [2. Use nn-Meter with the bench dataset](nn-meter_predictor_for_bench_dataset.ipynb) shows how to use nn-Meter to predict latency for the bench dataset. -Since the dataset is encoded in a graph format, we also provide an example [3. Use nn-Meter bench dataset for GNN training](nn-meter_dataset_for_gnn.ipynb) of using GCN to predict the model latency with the bench dataset. +Since the dataset is encoded in a graph format, we also provide an example [3. Use nn-Meter bench dataset for GNN training](nn-meter_dataset_for_gnn.ipynb) of using GNN to predict the model latency with the bench dataset. Finally, we provide more hardware-ware NAS examples in NNI. From 68e3e635c92f5c41849478cd866ef63fea48332f Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 15:43:20 +0800 Subject: [PATCH 14/18] add link for dataset in overview --- docs/overview.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/overview.md b/docs/overview.md index a2c3719b..92f4424b 100644 --- a/docs/overview.md +++ b/docs/overview.md @@ -21,4 +21,6 @@ If you have a new hardware to predict DNN latency, a re-run of nn-Meter is requ - [How to use nn-Meter Predictor](predictor/usage.md) -- [nn-meter in hardware-aware NAS](predictor/hardware-aware-model-design.md) \ No newline at end of file +- [nn-Meter in hardware-aware NAS](predictor/hardware-aware-model-design.md) + +- [nn-Meter bench dataset](dataset.py) \ No newline at end of file From 110d92c02ff6e7d9f1e23165d233730f5fce666f Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 15:49:41 +0800 Subject: [PATCH 15/18] move NumpyEncoder to utils --- nn_meter/nn_meter_cli.py | 2 +- nn_meter/utils/graph_tool.py | 12 +----------- nn_meter/utils/utils.py | 12 +++++++++++- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/nn_meter/nn_meter_cli.py b/nn_meter/nn_meter_cli.py index 36bfe7dd..8438fcb5 100644 --- a/nn_meter/nn_meter_cli.py +++ b/nn_meter/nn_meter_cli.py @@ -62,7 +62,7 @@ def get_nnmeter_ir_cli(args): """convert pb file or onnx file to nn-Meter IR graph according to the command line interface arguments """ import json - from nn_meter.utils.graph_tool import NumpyEncoder + from nn_meter.utils.utils import NumpyEncoder if args.tensorflow: graph = model_file_to_graph(args.tensorflow, 'pb') filename = args.output if args.output else args.tensorflow.replace(".pb", "_pb_ir.json") diff --git a/nn_meter/utils/graph_tool.py b/nn_meter/utils/graph_tool.py index 69c4f2ad..f88f6849 100644 --- a/nn_meter/utils/graph_tool.py +++ b/nn_meter/utils/graph_tool.py @@ -2,18 +2,8 @@ # Licensed under the MIT license. import copy import json -import numpy as np import logging - - -class NumpyEncoder(json.JSONEncoder): - def default(self, obj): - if isinstance(obj, np.ndarray): - return obj.tolist() - if isinstance(obj, (bytes, bytearray)): - return obj.decode("utf-8") - return json.JSONEncoder.default(self, obj) - +from .utils import NumpyEncoder class ModelGraph: def __init__(self, filename=None, graph=None): diff --git a/nn_meter/utils/utils.py b/nn_meter/utils/utils.py index 0deecdee..3ffd23e0 100644 --- a/nn_meter/utils/utils.py +++ b/nn_meter/utils/utils.py @@ -5,7 +5,8 @@ from tqdm import tqdm import requests import logging - +import json +import numpy as np def download_from_url(urladdr, ppath): """ @@ -34,3 +35,12 @@ def download_from_url(urladdr, ppath): zipfile.close() progress_bar.close() os.remove(file_name) + + +class NumpyEncoder(json.JSONEncoder): + def default(self, obj): + if isinstance(obj, np.ndarray): + return obj.tolist() + if isinstance(obj, (bytes, bytearray)): + return obj.decode("utf-8") + return json.JSONEncoder.default(self, obj) From bb2242c2cdee0cbc896f41d0367cd42cb145e67a Mon Sep 17 00:00:00 2001 From: jiahangxu Date: Tue, 9 Nov 2021 16:13:17 +0800 Subject: [PATCH 16/18] fix typo --- docs/overview.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/overview.md b/docs/overview.md index 92f4424b..2ee6020b 100644 --- a/docs/overview.md +++ b/docs/overview.md @@ -23,4 +23,4 @@ If you have a new hardware to predict DNN latency, a re-run of nn-Meter is requ - [nn-Meter in hardware-aware NAS](predictor/hardware-aware-model-design.md) -- [nn-Meter bench dataset](dataset.py) \ No newline at end of file +- [nn-Meter bench dataset](dataset.md) \ No newline at end of file From 03ffdc06f63a5681891c457ea6329d99bdac89c9 Mon Sep 17 00:00:00 2001 From: Li Lyna Zhang Date: Tue, 9 Nov 2021 17:38:47 +0800 Subject: [PATCH 17/18] Update dataset.md --- docs/dataset.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/dataset.md b/docs/dataset.md index 674abf1a..83fb4db3 100644 --- a/docs/dataset.md +++ b/docs/dataset.md @@ -4,5 +4,8 @@ To evaluate the effectiveness of a prediction model on an arbitrary DNN model, w We release the dataset, and provide an interface of `nn_meter.dataset` for users to get access to the dataset. This interface could automatically download the nn-Meter bench dataset and return the path of the dataset when calling. Users can also download the data from the [Download Link](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip) on their own. This [example](../examples/nn-meter_predictor_for_bench_dataset.ipynb) shows how to use nn-Meter predictor to predict latency for the bench dataset. +**Note that** to measure the inference latency of models in this dataset, we generate tensorflow pb and tflite models and measure their latency on the target devices. However, since it requires hundreds of GB storage to store the full dataset, we didn't include these model files. Instead, we parse the pb files and record the model structures and parameters in +`nn_meter.dataset`. + Since the dataset is encoded in a graph format, we also provide an interface of `nn_meter.dataset.gnn_dataloader` for GNN training. By this interface, `GNNDataset` and `GNNDataloader` build the model structure of the bench dataset in `.jsonl` format into GNN required dataset and data loader. Users could refer to this [example](../examples/nn-meter_dataset_for_gnn.ipynb) for further information of `gnn_dataloader`. Note that to apply nn-Meter bench dataset for GNN training, the package `torch` and `dgl` should be installed. From 243a07900768756bf20b22e0784524f072477ba4 Mon Sep 17 00:00:00 2001 From: Li Lyna Zhang Date: Tue, 9 Nov 2021 17:39:08 +0800 Subject: [PATCH 18/18] Update dataset.md --- docs/dataset.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/dataset.md b/docs/dataset.md index 83fb4db3..8a363410 100644 --- a/docs/dataset.md +++ b/docs/dataset.md @@ -4,7 +4,7 @@ To evaluate the effectiveness of a prediction model on an arbitrary DNN model, w We release the dataset, and provide an interface of `nn_meter.dataset` for users to get access to the dataset. This interface could automatically download the nn-Meter bench dataset and return the path of the dataset when calling. Users can also download the data from the [Download Link](https://github.com/microsoft/nn-Meter/releases/download/v1.0-data/datasets.zip) on their own. This [example](../examples/nn-meter_predictor_for_bench_dataset.ipynb) shows how to use nn-Meter predictor to predict latency for the bench dataset. -**Note that** to measure the inference latency of models in this dataset, we generate tensorflow pb and tflite models and measure their latency on the target devices. However, since it requires hundreds of GB storage to store the full dataset, we didn't include these model files. Instead, we parse the pb files and record the model structures and parameters in +**Note:** to measure the inference latency of models in this dataset, we generate tensorflow pb and tflite models and measure their latency on the target devices. However, since it requires hundreds of GB storage to store the full dataset, we didn't include these model files. Instead, we parse the pb files and record the model structures and parameters in `nn_meter.dataset`. Since the dataset is encoded in a graph format, we also provide an interface of `nn_meter.dataset.gnn_dataloader` for GNN training. By this interface, `GNNDataset` and `GNNDataloader` build the model structure of the bench dataset in `.jsonl` format into GNN required dataset and data loader. Users could refer to this [example](../examples/nn-meter_dataset_for_gnn.ipynb) for further information of `gnn_dataloader`. Note that to apply nn-Meter bench dataset for GNN training, the package `torch` and `dgl` should be installed.