Atlas 200I DK A2安装MindSpore Ascend版本

2024-05-26 09:52

本文主要是介绍Atlas 200I DK A2安装MindSpore Ascend版本,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

一、参考资料

mindspore快速安装

二、重要说明

经过博主多次尝试多个版本,Atlas 200I DK A2无法安装MindSpore Ascend版本

也有其他博主测试,也未尝成功,例如:【MindSpore易点通·漫游世界】在Atlas 200I DK A2 (CANN6.2.RC2)上安装MindSpore Ascend版的踩坑记录

mindspore 1.5.2 报错无法运行(./tensor_add_sample: symbol lookup error: /home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/lib/libmindspore.so: undefined symbol: _ZN2ge5Model8SetGraphERKNS_5GraphE)

mindspore 1.6.2 报错无法运行(./tensor_add_sample: symbol lookup error: /home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/lib/libmindspore.so: undefined symbol: _ZN2ge5Model8SetGraphERKNS_5GraphE)

mindspore 1.7.1 报错无法运行 (./tensor_add_sample: error while loading shared libraries: libhccl.so: cannot open shared object file: No such file or directory)

mindspore 1.8.1 报错无法运行(./tensor_add_sample: error while loading shared libraries: libhccl.so: cannot open shared object file: No such file or directory)

mindspore 1.9.0 报错无法运行(./tensor_add_sample: symbol lookup error: /home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/lib/libmindspore.so: undefined symbol: _ZN2ge5Model8SetGraphERKNS_5GraphE)

mindspore 1.10.1 报错无法运行(./tensor_add_sample: symbol lookup error: /home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/lib/libmindspore.so: undefined symbol: _ZN2ge5Model8SetGraphERKNS_5GraphE)

mindspore 2.0.0 报错无法运行(Unsupported device target Ascend)

mindspore 2.1.0 报错无法运行(Unsupported device target Ascend)

三、准备工作

1. 测试环境

设备型号:Atlas 200I DK A2
Operating System + Version: Ubuntu 22.04 LTS
CPU Type: 4核TAISHANV200M处理器
AI CPU number: 0
control CPU number: 4
RAM: 4GB 
miscroSD: 128GB
CANN Vertion: 7.0.RC1
HwHiAiUser@davinci-mini:~$ npu-smi info -t aicpu-config -i 0 -c 0Current AI CPU number          : 0Current control CPU number     : 4Number of AI CPUs set          : 0Number of control CPUs set     : 4

2. MindSpore与CANN版本对齐

通过 链接 查询MindSpore与Ascend配套软件包的版本配套关系。

在这里插入图片描述

3. 安装mindspore_ascend

详细过程,请参考:pip方式安装MindSpore Ascend 310版本

4. 验证是否安装成功

4.1 方法一

import mindspore as ms# ms.set_context(device_target='CPU')
# ms.set_context(device_target='GPU')
ms.set_context(device_target="Ascend")
ms.set_context(device_id=0)
mindspore.run_check()

如果输出以下结果,则说明mindspore_ascend安装成功。

MindSpore version: 版本号
The result of multiplication calculation is correct, MindSpore has been installed on platform [Ascend] successfully!

4.2 方法二

import numpy as np
import mindspore as ms
import mindspore.ops as opsms.set_context(device_target="Ascend")
x = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32))
y = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32))
print(ops.add(x, y))

如果输出以下结果,则说明mindspore_ascend安装成功。

[[[[2. 2. 2. 2.][2. 2. 2. 2.][2. 2. 2. 2.]][[2. 2. 2. 2.][2. 2. 2. 2.][2. 2. 2. 2.]][[2. 2. 2. 2.][2. 2. 2. 2.][2. 2. 2. 2.]]]]

4.3 方法三

ascend310_single_op_sample

这是一个[1, 2, 3, 4][2, 3, 4, 5]相加的简单样例,代码工程目录结构如下:

└─ascend310_single_op_sample├── CMakeLists.txt                    // 编译脚本├── README.md                         // 使用说明├── main.cc                           // 主函数└── tensor_add.mindir                 // MindIR模型文件
unzip ascend310_single_op_sample.zip
cd ascend310_single_op_sample# 编译
cmake . -DMINDSPORE_PATH=`pip show mindspore-ascend | grep Location | awk '{print $2"/mindspore"}' | xargs realpath`
make# 执行
./tensor_add_sample

如果输出以下结果,则说明mindspore_ascend安装成功。

3
5
7
9

四、测试代码

1. 示例一

用MindSpore搭建模型,并进行测试。

"""
MindSpore implementation of `MobileNetV1`.
Refer to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
"""
import timefrom mindspore import nn, Tensor, ops
import mindspore.common.initializer as init
import mindspore as ms
from PIL import Image
from mindcv.data import create_transforms
import numpy as npdef depthwise_separable_conv(inp: int, oup: int, stride: int) -> nn.SequentialCell:return nn.SequentialCell(# dwnn.Conv2d(inp, inp, 3, stride, pad_mode="pad", padding=1, group=inp, has_bias=False),nn.BatchNorm2d(inp),nn.ReLU(),# pwnn.Conv2d(inp, oup, 1, 1, pad_mode="pad", padding=0, has_bias=False),nn.BatchNorm2d(oup),nn.ReLU(),)class MobileNetV1(nn.Cell):r"""MobileNetV1 model class, based on`"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" <https://arxiv.org/abs/1704.04861>`_Args:alpha: scale factor of model width. Default: 1.in_channels: number the channels of the input. Default: 3.num_classes: number of classification classes. Default: 1000."""def __init__(self,alpha: float = 1.,in_channels: int = 3,num_classes: int = 1000) -> None:super().__init__()input_channels = int(32 * alpha)# Setting of depth-wise separable conv# c: number of output channel# s: stride of depth-wise convblock_setting = [# c, s[64, 1],[128, 2],[128, 1],[256, 2],[256, 1],[512, 2],[512, 1],[512, 1],[512, 1],[512, 1],[512, 1],[1024, 2],[1024, 1],]features = [nn.Conv2d(in_channels, input_channels, 3, 2, pad_mode="pad", padding=1, has_bias=False),nn.BatchNorm2d(input_channels),nn.ReLU()]for c, s in block_setting:output_channel = int(c * alpha)features.append(depthwise_separable_conv(input_channels, output_channel, s))input_channels = output_channelself.features = nn.SequentialCell(features)# self.pool = GlobalAvgPooling()self.pool = nn.AdaptiveAvgPool2d(output_size=(1, 1))self.classifier = nn.Dense(input_channels, num_classes)self._initialize_weights()def _initialize_weights(self) -> None:"""Initialize weights for cells."""for _, cell in self.cells_and_names():if isinstance(cell, nn.Conv2d):cell.weight.set_data(init.initializer(init.XavierUniform(),cell.weight.shape,cell.weight.dtype))if isinstance(cell, nn.Dense):cell.weight.set_data(init.initializer(init.TruncatedNormal(),cell.weight.shape,cell.weight.dtype))def forward_features(self, x: Tensor) -> Tensor:x = self.features(x)return xdef forward_head(self, x: Tensor) -> Tensor:squeeze = ops.Squeeze(0)x = squeeze(x)x = self.pool(x)squeeze = ops.Squeeze(2)x = squeeze(x)x = x.transpose()x = self.classifier(x)return xdef construct(self, x: Tensor) -> Tensor:x = self.forward_features(x)x = self.forward_head(x)return xdef mobilenet_v1_100_224(pretrained: bool = False, num_classes: int = 1000, in_channels=3, **kwargs) -> MobileNetV1:"""Get MobileNetV1 model without width scaling.Refer to the base class `models.MobileNetV1` for more details."""model = MobileNetV1(alpha=1.0, in_channels=in_channels, num_classes=num_classes, **kwargs)return modelif __name__ == '__main__':# ms.set_context(device_target='GPU')# ms.set_context(device_target='CPU')ms.set_context(device_target="Ascend")ms.set_context(device_id=0)ms.set_seed(1)ms.set_context(mode=ms.PYNATIVE_MODE)img = Image.open("image.jpg").convert("RGB")# create transformtransform_list = create_transforms(dataset_name="imagenet",is_training=False,)transform_list.pop(0)for transform in transform_list:img = transform(img)img = np.expand_dims(img, axis=0)# create modelnetwork = mobilenet_v1_100_224()for i in range(100):# warmupnetwork(ms.Tensor(img))time_begin = time.time()for i in range(1000):# predictnetwork(ms.Tensor(img))time_total = (time.time() - time_begin) * 1000 / 1000print(f"total time is: {time_total}")# print(network)

2. 示例二

调用 mindcv库中的预训练模型进行测试。

"""MindSpore Inference Script
"""import numpy as np
from PIL import Imageimport mindspore as msfrom mindcv.data import create_transforms
from mindcv.models import create_model
import time# ms.set_context(device_target='CPU')
# ms.set_context(device_target='GPU')ms.set_context(device_target='Ascend')
ms.set_context(device_id=0)
ms.set_context(max_device_memory="3.5GB")def main():ms.set_seed(1)ms.set_context(mode=ms.PYNATIVE_MODE)img = Image.open("image.jpg").convert("RGB")# create transformtransform_list = create_transforms(dataset_name="imagenet",is_training=False,)transform_list.pop(0)for transform in transform_list:img = transform(img)img = np.expand_dims(img, axis=0)# create modelnetwork = create_model(model_name="mobilenet_v1_100",  # mobilenet_v1_100_224pretrained=False,)network.set_train(False)for i in range(100):# warmupnetwork(ms.Tensor(img))time_begin = time.time()for i in range(1000):# predictnetwork(ms.Tensor(img))time_total = (time.time() - time_begin) * 1000 / 1000print(f"total time is: {time_total}")if __name__ == "__main__":main()

五、FAQ

Q:RuntimeError: Load op info form json config failed, version: Ascend310B4

[WARNING] ME(230369:255086392991776,MainProcess):2024-05-25-17:29:28.302.942 [mindspore/run_check/_check_version.py:375] MindSpore version 2.1.1 and "te" wheel package version 7.0 does not match. For details, refer to the installation guidelines: https://www.mindspore.cn/install
[WARNING] ME(230369:255086392991776,MainProcess):2024-05-25-17:29:28.305.619 [mindspore/run_check/_check_version.py:382] MindSpore version 2.1.1 and "hccl" wheel package version 7.0 does not match. For details, refer to the installation guidelines: https://www.mindspore.cn/install
[WARNING] ME(230369:255086392991776,MainProcess):2024-05-25-17:29:28.305.849 [mindspore/run_check/_check_version.py:396] Please pay attention to the above warning, countdown: 3
[WARNING] ME(230369:255086392991776,MainProcess):2024-05-25-17:29:29.307.139 [mindspore/run_check/_check_version.py:396] Please pay attention to the above warning, countdown: 2
[WARNING] ME(230369:255086392991776,MainProcess):2024-05-25-17:29:30.308.249 [mindspore/run_check/_check_version.py:396] Please pay attention to the above warning, countdown: 1
[ERROR] KERNEL(230369,e7ffaf56f120,python):2024-05-25-17:29:35.761.869 [mindspore/ccsrc/kernel/oplib/op_info_utils.cc:172] LoadOpInfoJson] Get op info json suffix path failed, soc_version: Ascend310B4
[ERROR] KERNEL(230369,e7ffaf56f120,python):2024-05-25-17:29:35.762.199 [mindspore/ccsrc/kernel/oplib/op_info_utils.cc:111] GenerateOpInfos] Load op info json failed, version: Ascend310B4
Traceback (most recent call last):File "/root/Downloads/mindspore_ascend_demo.py", line 8, in <module>print(ops.add(x, y))File "/usr/local/miniconda3/envs/mindspore22/lib/python3.9/site-packages/mindspore/common/_stub_tensor.py", line 49, in funreturn method(*arg, **kwargs)File "/usr/local/miniconda3/envs/mindspore22/lib/python3.9/site-packages/mindspore/common/tensor.py", line 486, in __str__return str(self.asnumpy())File "/usr/local/miniconda3/envs/mindspore22/lib/python3.9/site-packages/mindspore/common/tensor.py", line 924, in asnumpyreturn Tensor_.asnumpy(self)
RuntimeError: Load op info form json config failed, version: Ascend310B4----------------------------------------------------
- C++ Call Stack: (For framework developers)
----------------------------------------------------
mindspore/ccsrc/plugin/device/ascend/hal/device/ascend_kernel_runtime.cc:431 Init[ERROR] PIPELINE(230369,e7ffedd76020,python):2024-05-25-17:29:35.824.442 [mindspore/ccsrc/pipeline/jit/pipeline.cc:2311] ClearResAtexit] Check exception before process exit: Load op info form json config failed, version: Ascend310B4----------------------------------------------------
- C++ Call Stack: (For framework developers)
----------------------------------------------------
mindspore/ccsrc/plugin/device/ascend/hal/device/ascend_kernel_runtime.cc:431 Init

mindspore_ascend 2.1.1 测试失败。

Q:RuntimeError: The device address type is wrong: type name in address:CPU, type name in context:Ascend

RuntimeError: The device address type is wrong: type name in address:CPU, type name in context:Ascend----------------------------------------------------
- C++ Call Stack: (For framework developers)
----------------------------------------------------
mindspore/ccsrc/plugin/device/ascend/hal/hardware/ge_device_res_manager.cc:72 AllocateMemory

mindspore_ascend 2.2.0 测试失败。

这篇关于Atlas 200I DK A2安装MindSpore Ascend版本的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/1004132

相关文章

Linux系统中卸载与安装JDK的详细教程

《Linux系统中卸载与安装JDK的详细教程》本文详细介绍了如何在Linux系统中通过Xshell和Xftp工具连接与传输文件,然后进行JDK的安装与卸载,安装步骤包括连接Linux、传输JDK安装包... 目录1、卸载1.1 linux删除自带的JDK1.2 Linux上卸载自己安装的JDK2、安装2.1

Linux卸载自带jdk并安装新jdk版本的图文教程

《Linux卸载自带jdk并安装新jdk版本的图文教程》在Linux系统中,有时需要卸载预装的OpenJDK并安装特定版本的JDK,例如JDK1.8,所以本文给大家详细介绍了Linux卸载自带jdk并... 目录Ⅰ、卸载自带jdkⅡ、安装新版jdkⅠ、卸载自带jdk1、输入命令查看旧jdkrpm -qa

Tomcat版本与Java版本的关系及说明

《Tomcat版本与Java版本的关系及说明》:本文主要介绍Tomcat版本与Java版本的关系及说明,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录Tomcat版本与Java版本的关系Tomcat历史版本对应的Java版本Tomcat支持哪些版本的pythonJ

MySQL Workbench 安装教程(保姆级)

《MySQLWorkbench安装教程(保姆级)》MySQLWorkbench是一款强大的数据库设计和管理工具,本文主要介绍了MySQLWorkbench安装教程,文中通过图文介绍的非常详细,对大... 目录前言:详细步骤:一、检查安装的数据库版本二、在官网下载对应的mysql Workbench版本,要是

Linux安装MySQL的教程

《Linux安装MySQL的教程》:本文主要介绍Linux安装MySQL的教程,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录linux安装mysql1.Mysql官网2.我的存放路径3.解压mysql文件到当前目录4.重命名一下5.创建mysql用户组和用户并修

IDEA中Git版本回退的两种实现方案

《IDEA中Git版本回退的两种实现方案》作为开发者,代码版本回退是日常高频操作,IntelliJIDEA集成了强大的Git工具链,但面对reset和revert两种核心回退方案,许多开发者仍存在选择... 目录一、版本回退前置知识二、Reset方案:整体改写历史1、IDEA图形化操作(推荐)1.1、查看提

pip无法安装osgeo失败的问题解决

《pip无法安装osgeo失败的问题解决》本文主要介绍了pip无法安装osgeo失败的问题解决,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一... 进入官方提供的扩展包下载网站寻找版本适配的whl文件注意:要选择cp(python版本)和你py

JDK多版本共存并自由切换的操作指南(本文为JDK8和JDK17)

《JDK多版本共存并自由切换的操作指南(本文为JDK8和JDK17)》本文介绍了如何在Windows系统上配置多版本JDK(以JDK8和JDK17为例),并通过图文结合的方式给大家讲解了详细步骤,具有... 目录第一步 下载安装JDK第二步 配置环境变量第三步 切换JDK版本并验证可能遇到的问题前提:公司常

Android App安装列表获取方法(实践方案)

《AndroidApp安装列表获取方法(实践方案)》文章介绍了Android11及以上版本获取应用列表的方案调整,包括权限配置、白名单配置和action配置三种方式,并提供了相应的Java和Kotl... 目录前言实现方案         方案概述一、 androidManifest 三种配置方式

nvm如何切换与管理node版本

《nvm如何切换与管理node版本》:本文主要介绍nvm如何切换与管理node版本问题,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录nvm切换与管理node版本nvm安装nvm常用命令总结nvm切换与管理node版本nvm适用于多项目同时开发,然后项目适配no