x86 cpu卷积网络的自动调谐

最新推荐文章于 2024-04-03 07:24:39 发布

wujianming_110117

最新推荐文章于 2024-04-03 07:24:39 发布

阅读量587

点赞数

CC 4.0 BY-SA版权

分类专栏： GPU，NPU，XPU，DPU，MPU 算法文章标签： TensorRT

吴建明

本文链接：https://blog.csdn.net/wujianing_110117/article/details/111149186

本文档详细介绍了如何针对x86 CPU进行卷积神经网络的自动调优，包括设置目标CPU、定义网络、设置线程数、配置调优选项等步骤，以提高内核执行性能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

x86 cpu卷积网络的自动调谐
这是一个关于如何为x86cpu调整卷积神经网络的文档。
本文不会在Windows或最新版本的macOS上运行。要让它运行，需要将主体包装在
if name == “main”: 块中。
import os
import numpy as np

import tvm
from tvm import relay, autotvm
from tvm.relay import testing
from tvm.autotvm.tuner import XGBTuner, GATuner, RandomTuner, GridSearchTuner
from tvm.autotvm.graph_tuner import DPTuner, PBQPTuner
import tvm.contrib.graph_runtime as runtime
Define network
首先需要在中继前端API中定义网络。可以从relay.testing测试或编译
relay.testing.resnet转换。也可以从MXNet、ONNX和TensorFlow加载模型。本文选择restuning作为示例。
def get_network(name, batch_size):
“”“Get the symbol definition and random weight of a network”""
input_shape = (batch_size, 3, 224, 224)
output_shape = (batch_size, 1000)

if "resnet" in name:
    n_layer = int(name.split("-")[1])
    mod, params = relay.testing.resnet.get_workload(
        num_layers=n_layer, batch_size=batch_size, dtype=dtype
    )
elif "vgg" in name:
    n_layer = int(name.split("-")[1])
    mod, params = relay.testing.vgg.get_workload(
        num_layers=n_layer, batch_size=batch_size, dtype=dtype
    )
elif name == "mobilenet":
    mod, params = relay.testing.mobilenet.get_workload(batch_size=batch_size, dtype=dtype)
elif name == "squeezenet_v1.1":
    mod, params = relay.testing.squeezenet.get_workload(
        batch_size=batch_size, version="1.1", dtype=dtype
    )
elif name == "inception_v3":
    input_shape = (batch_size, 3, 299, 299)
    mod, params = relay.testing.inception_v3.get_workload(batch_size=batch_size, dtype=dtype)
elif name == "mxnet":
    # an example for mxnet model
    from mxnet.gluon.model_zoo.vision import get_model

    block = get_model("resnet18_v1", pretrained=True)
    mod, params = relay.frontend.from_mxnet(block, shape=