MNN配置
作者:互联网
1、github链接:https://github.com/alibaba/MNN/tree/master/tools/converter
2、教程
(1)使用教程:https://www.bookstack.cn/read/MNN-zh/tools-converter-README_CN.md
(2)参考博客:https://blog.csdn.net/qq_37643960/article/details/97028743
(3)github的项目中的readme部分也有讲解;
安装过程:
编译安装MNN动态库和Convert转换工具,命令如下:
cd /MNN/ mkdir build cd build cmake .. -DMNN_BUILD_CONVERTER=true make -j4
之后build文件夹中就会出现benchmark.out和MNNConvert可执行文件;
测试benchmark.out:
./benchmark.out ../benchmark/models/ 10 0
其中10表示前向传播10次,最后结果取平均值;0表示使用CPU;(执行推理的计算设备,有效值为 0(浮点 CPU)、1(Metal)、3(浮点OpenCL)、6(OpenGL),7(Vulkan))
测试MNNConvert:
./MNNConvert -h
测试:
第一步:将pytorch模型转换为onnx模型
import torch import torchvision dummy_input = torch.randn(10, 3, 224, 224, device='cuda') model = torchvision.models.alexnet(pretrained=True).cuda() # Providing input and output names sets the display names for values # within the model's graph. Setting these does not change the semantics # of the graph; it is only for readability. # # The inputs to the network consist of the flat list of inputs (i.e. # the values you would pass to the forward() method) followed by the # flat list of parameters. You can partially specify names, i.e. provide # a list here shorter than the number of inputs to the model, and we will # only set that subset of names, starting from the beginning. input_names = [ "actual_input_1" ] + [ "learned_%d" % i for i in range(16) ] output_names = [ "output1" ] torch.onnx.export(model, dummy_input, "alexnet.onnx", verbose=True, input_names=input_names, output_names=output_names)
第二步:将onnx模型转换为mnn模型
./MNNConvert -f ONNX --modelFile alexnet.onnx --MNNModel alexnet.mnn --bizCode MNN
第三步:使用benchmark.out测试前向传播时间
./benchmark.out ./models/ 10 0
PS:在/MNN/source/shape/ShapeSqueeze.cpp 80L中:注释掉那个NanAssert(),在新版函数中已经将它注释掉了;(要不然会报reshape的error)
标签:onnx,配置,benchmark,names,MNN,input,out 来源: https://www.cnblogs.com/zf-blog/p/11890537.html