ps制作网站效果图,个人品牌建设,百度收录网站中文称,万科文章目录 前言一、平台环境准备二、环境准备1.GFPGAN代码处理2.MagicMind转换修改env.sh修改run.sh参数解析运行 3.修改后模型运行 前言
MagicMind是面向寒武纪MLU的推理加速引擎。MagicMind能将人工智能框架#xff08;TensorFlow、PyTorch、Caffe与ONNX等#xff09;训练好… 文章目录 前言一、平台环境准备二、环境准备1.GFPGAN代码处理2.MagicMind转换修改env.sh修改run.sh参数解析运行 3.修改后模型运行 前言
MagicMind是面向寒武纪MLU的推理加速引擎。MagicMind能将人工智能框架TensorFlow、PyTorch、Caffe与ONNX等训练好的算法模型转换成MagicMind统一计算图表示并提供端到端的模型优化、代码生成以及推理业务部署能力。MagicMind 致力于为用户提供高性能、灵活、易用的编程接口以及配套工具让用户能够专注于推理业务开发和部署本身而无需过多关注底层硬件细节。 如果有用MLU、GPU、CPU训练好的算法模型可以使用MagicMind快速地实现在MLU上部署推理业务。MagicMind的优势在于它能为MLU上的推理业务提供
极致的性能优化。可靠的精度。尽可能少的内存占用。灵活的定制化开发能力。简洁易用的接口。MagicMind适用但不限于以下推理业务场景
图像处理分类、检测、分割。视频处理。自然语言处理。姿态检测。搜索、推荐。MagicMind支持不同的系统平台和MLU硬件平台。MagicMind面向云端业务和端侧业务提供了统一的编程界面并针对两种业务场景的差异点提供了必要的定制化功能比如面向端侧部署提供了remote debug功能。
具体参考https://www.cambricon.com/docs/sdk_1.15.0/magicmind_1.7.0/user_guide/2_introduction/0_what_is_magicmind/what_is_magicmind.html 一、平台环境准备
镜像选择pytorch:v24.10-torch2.4.0-torchmlu1.23.1-ubuntu22.04-py310 【本次mm操作对镜像需求不是很高只需对其相关版本即可】 卡选择任意一款MLU3系列及以上卡
二、环境准备
1.GFPGAN代码处理
git clone https://github.com/xuanandsix/GFPGAN-onnxruntime-demo.git
#下载gfpgan原始模型
wget https://githubfast.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth
#转onnx操作
python torch2onnx.py --src_model_path ./GFPGANv1.4.pth --dst_model_path ./GFPGANv1.4.onnx --img_size 512
#onnx推理
python demo_onnx.py --model_path GFPGANv1.4.onnx --image_path ./cropped_faces/Adele_crop.png --save_path Adele_v3.jpg性能
(pytorch) rootnotebook-mm-100semv-notebook-0:/workspace/volume/guojunceshi2/mmgfpgan/GFPGAN-onnxruntime-demo# python demo_onnx.py
infer time: 2.8468078281730413
infer time: 2.2596635334193707
infer time: 3.1177305486053232.MagicMind转换
#mmwhl包安装
pip install magicmind-1.13.0-cp310-cp310-linux_x86_64.whl
#代码拷贝
git clone https://gitee.com/cambricon/magicmind_cloud.git
#1,环境变量配置
cd magicmind_cloud/buildin/cv/classification/resnet50_onnx/修改env.sh export NEUWARE_HOME/usr/local/neuware #主要是这一行重要其余不变
export MM_RUN_PATH${NEUWARE_HOME}/bin
#本sample工作路径
export PROJ_ROOT_PATH$(cd $(dirname ${BASH_SOURCE[0]});pwd)
export MAGICMIND_CLOUD${PROJ_ROOT_PATH%buildin*}
export MODEL_PATH${PROJ_ROOT_PATH}/data/models# CV类网络通用文件路径
export UTILS_PATH${MAGICMIND_CLOUD}/buildin/cv/utils# Python公共组件路径
export PYTHON_COMMON_PATH${MAGICMIND_CLOUD}/buildin/python_common
# CPP公共接口路径
export CPP_COMMON_PATH$MAGICMIND_CLOUD/buildin/cpp_commonhas_add_common_path$(echo ${PYTHONPATH}|grep ${PYTHON_COMMON_PATH})
if [ -z ${has_add_common_path} ];thenexport PYTHONPATH${PYTHONPATH}:${PYTHON_COMMON_PATH}
fihas_add_util_path$(echo ${PYTHONPATH}|grep ${UTILS_PATH})
if [ -z ${has_add_util_path} ];thenexport PYTHONPATH${PYTHONPATH}:${UTILS_PATH}
fi
然后source env.sh
修改run.sh
#!/bin/bash
set -e
set -xmagicmind_modelface_force_float32_true
precisionforce_float32
batch_size1
dynamic_shapefalsepython gen_model.py --precision ${precision} \--input_dims ${batch_size} 3 512 512 \--batch_size ${batch_size} \-dynamic_shape ${dynamic_shape} \--magicmind_model ${magicmind_model} \--input_layout NHWC \--dim_range_min 1 3 512 512 \--dim_range_max 64 3 512 512 \--onnx /workspace/volume/guojunceshi2/mmgfpgan/GFPGAN-onnxruntime-demo/gfpgan14.onnx参数解析
–precision 可选。精度模式默认采用float32运行整个网络即值为:force_float32。force_float32:所有算子以FLOAT32作为输入精度和输出数据类型,且中间结果也是FLOAT32。force float16:所有算子以FLOAT16作为输入精度和输出数据类型,且中间结果也是FLOAT16。qint8_mixed float32:模拟量化算子以FLOAT32作为输入先量化成INT8再转成FLOAT32进行计算其他非量化算子的输入精度和输出数据类型和中间结果都是FLOAT32。qint16_mixed_foat32:模拟量化算子以FLOAT32作为输入,先量化成INT16,再转成FLOAT32进行计算其他非量化算子的输入精度和输出数据类型和中间结果都是FLOAT32。 qint8_mixed _float16:模拟量化算子以FLOAT16作为输入先量化成INT8再转成FLOAT16进行计算其他非量化算子的输入精度和输出数据类型和中间结果都是FLOAT16。ONNX支持的模拟量化算子包括:Conv1DConv2D,Conv3D,ConvTranspose1DConvTrans-pose2DGemmMatMul。模拟量化相关概念见模拟量化。
–input_dims 输入维度 –dynamic_shape
运行
生成 face_force_float32_true文件 注意输入维度和输出维度
3.修改后模型运行
原始模型读取部分
img img.transpose(0, 3, 1, 2)
pre_process 返回为13512512注意img输入维度为13512512
ort_inputs {self.ort_session.get_inputs()[0].name: img}
ort_outs self.ort_session.run(None, ort_inputs)修改后
img img.transpose(0, 1, 2, 3)
pre_process 返回为15125123
模型读取部分修改为其余不变
记得推理前执行以下前面source env.sh操作
from mm_runner import MMRunner
self.ort_session MMRunner(mm_file face_force_float32_true,device_id 0)
ort_outs self.ort_session([img])运行效果
2025-01-06 10:49:16,886: INFO: mm_runner.py:20] Model instance Created Success!
2025-01-06 10:49:16,898: INFO: mm_runner.py:32] Model dev Created Success!
2025-01-06 10:49:17,516: INFO: mm_runner.py:39] Model engine Created Success!
2025-01-06 10:49:17,644: INFO: mm_runner.py:43] Model context Created Success!
2025-01-06 10:49:17,645: INFO: mm_runner.py:47] Model queue Created Success!
2025-01-06 10:49:17,645: INFO: mm_runner.py:50] Model inputs Created Success!
2025-01-06 10:49:17,645: INFO: mm_runner.py:51] All Model resource Created Success!
infer time: 0.11474167183041573
infer time: 0.04283882491290569
infer time: 0.040602266788482666
infer time: 0.04028203524649143
infer time: 0.04049760662019253
infer time: 0.04016706347465515
infer time: 0.04045788757503033
infer time: 0.04026786610484123
infer time: 0.041572125628590584
infer time: 0.04047401808202267
infer time: 0.04045314900577068
infer time: 0.04047247767448425
infer time: 0.04037348926067352
infer time: 0.04047695733606815
infer time: 0.04112406447529793显存消耗
Every 2.0s: cnmon notebook-mm-100semv-notebook-0: Mon Jan 6 10:49:26 2025Mon Jan 6 10:49:26 2025
------------------------------------------------------------------------------
| CNMON v5.10.29 Driver v5.10.29 |
----------------------------------------------------------------------------
| Card VF Name Firmware | Bus-Id | Util Ecc-Error |
| Fan Temp Pwr:Usage/Cap | Memory-Usage | Mode Compute-Mode |
||
| 0 / MLU370-M8 v1.1.4 | 0000:69:00.0 | 73% 0 |
| 0% 34C 179 W/ 300 W | 731 MiB/ 42396 MiB | FULL Default |
----------------------------------------------------------------------------
| 1 / MLU370-M8 v1.1.4 | 0000:72:00.0 | 0% 0 |
| 0% 27C 50 W/ 300 W | 0 MiB/ 42396 MiB | FULL Default |
----------------------------------------------------------------------------------------------------------------------------------------------------------
| Processes: |
| Card MI PID Command Line MLU Memory Usage |
||
| 0 / 40007 python 650 MiB |
------------------------------------------------------------------------------优化前2.84-3.0s
优化后0.04-0.1s
