【CANN训练营】体验基于Caffe ResNet-50网络实现图片分类实践操作

实例功能

很简单的一个实例，功能就是一个实现图片分类的功能，然后拓展实现以下

将一张YUV420SP格式的图片编码为*.jpg格式的图片。
将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，缩放，再进行模型推理，分别得到两张图片的推理结果后，处理推理结果，输出最大置信度的类别标识以及top5置信度的总和。
将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，抠图，再进行模型推理，分别得到两张图片的推理结果后，处理推理结果，输出最大置信度的类别标识以及top5置信度的总和。
将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，抠图贴图，再进行模型推理，分别得到两张图片的推理结果后，处理推理结果，输出最大置信度的类别标识以及top5置信度的总和。
将YUV420SP NV12格式的图片（分辨率8192*8192）缩放，得到4000*4000。

环境及环境版本介绍

NPU：Ascend910（32GB）

CANN版本：CANN-8.0.RC3.alpha001

开始实践

创建conda环境

conda create -n cann_demopython=3.8-y conda activate cann_demo

安装CANN

wgethttps://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C20SPC703/Ascend-cann-toolkit_8.0.0.alpha003_linux-aarch64.runbashAscend-cann-toolkit_8.0.0.alpha003_linux-aarch64.run --full

激活环境变量

source/home/ma-user/Ascend/ascend-toolkit/set_env.sh

下载体验代码仓

gitclone -b v0.3-8.0.0.alpha003 https://gitee.com/Ascend/samples

进入示例文件夹

cdsamples/cplusplus/level2_simple_inference/1_classification/vpc_jpeg_resnet50_imagenet_classification

获取ResNet-50原始模型

下载模型CAFFE文件

cdcaffe_modelwgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/003_Atc_Models/AE/ATC%20Model/resnet50/resnet50.caffemodelwgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/003_Atc_Models/AE/ATC%20Model/resnet50/resnet50.prototxtcd..

安装依赖

pipinstalldecorator attrs psutil sympy scipy

转换模型

atc --model=caffe_model/resnet50.prototxt --weight=caffe_model/resnet50.caffemodel --framework=0--soc_version=Ascend910 --insert_op_conf=caffe_model/aipp.cfg --output=model/resnet50_aipp

准备测试图片

cddatawgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/models/aclsample/dvpp_vpc_8192x8192_nv12.yuvwgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/models/aclsample/persian_cat_1024_1536_283.jpgwgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/models/aclsample/wood_rabbit_1024_1061_330.jpgwgethttps://obs-9be7.obs.cn-east-2.myhuaweicloud.com/models/aclsample/wood_rabbit_1024_1068_nv12.yuvcd..

编译运行

安装依赖

condainstall-c conda-forge cmake condainstall-c conda-forge binutils

创建目录

mkdir-p build/intermediates/host

设置环境变量

source/home/ma-user/Ascend/ascend-toolkit/set_env.shexportDDK_PATH=$HOME/Ascend/ascend-toolkit/latestexportNPU_HOST_LIB=$DDK_PATH/runtime/lib64/stub

生成编译文件

cdbuild/intermediates/host cmake../../../src -DCMAKE_CXX_COMPILER=g++ -DCMAKE_SKIP_RPATH=TRUEmake

运行

设置main文件权限为可运行

cd ../../../out chmod +x main

将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，缩放，再进行模型推理，分别得到两张图片的推理结果

./main0

运行结果

[INFO] ./main param, param represents a vpc feature and must be set [INFO] start check result fold:./result [INFO] make directory successfully. [INFO] check result success, fold exist [INFO] acl init success [INFO] set device 0 success [INFO] create context success [INFO] create stream success [INFO] get run mode success [INFO] dvpp init resource success [INFO] load model ../model/resnet50_aipp.om success [INFO] create model description success [INFO] create model output success [INFO] model input width 224, input height 224 [INFO] ------------------------------------------- [INFO] start to process picture:../data/persian_cat_1024_1536_283.jpg [INFO] call JpegD [INFO] call vpcResize [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[283], top1[0.969727], top5[0.979855] [INFO] ------------------------------------------- [INFO] start to process picture:../data/wood_rabbit_1024_1061_330.jpg [INFO] call JpegD [INFO] call vpcResize [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[331], top1[0.895508], top5[1.000134] [INFO] ------------------------------------------- [INFO] unload model success, modelId is 1 [INFO] destroy model description success [INFO] destroy model output success [INFO] execute sample success [INFO] end to destroy stream [INFO] end to destroy context [INFO] end to reset device 0 [INFO] end to finalize acl

将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，抠图，再进行模型推理，分别得到两张图片的推理结果。

./main1

运行结果

[INFO] ./main param, param represents a vpc feature and must be set [INFO] start check result fold:./result [INFO] check result success, fold exist [INFO] acl init success [INFO] set device 0 success [INFO] create context success [INFO] create stream success [INFO] get run mode success [INFO] dvpp init resource success [INFO] load model ../model/resnet50_aipp.om success [INFO] create model description success [INFO] create model output success [INFO] model input width 224, input height 224 [INFO] ------------------------------------------- [INFO] start to process picture:../data/persian_cat_1024_1536_283.jpg [INFO] call JpegD [INFO] call vpcCrop [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[283], top1[0.996094], top5[0.999629] [INFO] ------------------------------------------- [INFO] start to process picture:../data/wood_rabbit_1024_1061_330.jpg [INFO] call JpegD [INFO] call vpcCrop [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[330], top1[0.859863], top5[1.000106] [INFO] ------------------------------------------- [INFO] unload model success, modelId is 1 [INFO] destroy model description success [INFO] destroy model output success [INFO] execute sample success [INFO] end to destroy stream [INFO] end to destroy context [INFO] end to reset device 0 [INFO] end to finalize acl

将两张*.jpg格式的解码成两张YUV420SP NV12格式的图片，抠图贴图，再进行模型推理，分别得到两张图片的推理结果。

./main2

运行结果

[INFO] ./main param, param represents a vpc feature and must be set [INFO] start check result fold:./result [INFO] check result success, fold exist [INFO] acl init success [INFO] set device 0 success [INFO] create context success [INFO] create stream success [INFO] get run mode success [INFO] dvpp init resource success [INFO] load model ../model/resnet50_aipp.om success [INFO] create model description success [INFO] create model output success [INFO] model input width 224, input height 224 [INFO] ------------------------------------------- [INFO] start to process picture:../data/persian_cat_1024_1536_283.jpg [INFO] call JpegD [INFO] call vpcCropAndPaste [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[283], top1[0.431885], top5[0.751892] [INFO] ------------------------------------------- [INFO] start to process picture:../data/wood_rabbit_1024_1061_330.jpg [INFO] call JpegD [INFO] call vpcCropAndPaste [INFO] Process dvpp success [INFO] create model input success [INFO] model execute success [INFO] destroy model input success [INFO] result : classType[330], top1[0.685059], top5[0.969410] [INFO] ------------------------------------------- [INFO] unload model success, modelId is 1 [INFO] destroy model description success [INFO] destroy model output success [INFO] execute sample success [INFO] end to destroy stream [INFO] end to destroy context [INFO] end to reset device 0 [INFO] end to finalize acl

将一张YUV420SP格式的图片编码为*.jpg格式的图片。

./main3

运行结果

[INFO] ./main param, param represents a vpc feature and must be set [INFO] start check result fold:./result [INFO] check result success, fold exist [INFO] acl init success [INFO] set device 0 success [INFO] create context success [INFO] create stream success [INFO] get run mode success [INFO] dvpp init resource success [INFO] start to jpege picture ../data/wood_rabbit_1024_1068_nv12.yuv [INFO] end to destroy stream [INFO] end to destroy context [INFO] end to reset device 0 [INFO] end to finalize acl

将一张分辨率为8192*8192的YUV420SP格式的图片缩放至4000*4000。

./main4

运行结果

[INFO] ./main param, param represents a vpc feature and must be set [INFO] start check result fold:./result [INFO] check result success, fold exist [INFO] acl init success [INFO] set device 0 success [INFO] create context success [INFO] create stream success [INFO] get run mode success [INFO] dvpp process 8k resize begin [INFO] dvpp init resource success [INFO] dvpp process 8k resize success [INFO] end to destroy stream [INFO] end to destroy context [INFO] end to reset device 0 [INFO] end to finalize acl