photo

guiyang


Last seen: 5 months ago Active since 2024

Followers: 0   Following: 0

Statistics

  • Thankful Level 1

View badges

Feeds

View by

Question


我在matlab中使用强化学习进行控制在actor的网络最后一层用的是tanhlayer,那么输出的范围应该在-1到1,但是输出的大小却不是
actorNet = [ featureInputLayer(numObs, Name="StateInLyr") fullyConnectedLayer(64) reluLayer fullyConnectedLa...

6 months ago | 1 answer | 0

1

answer

Question


我从pytorch中导入net到工作区,在把net导入到simulink中的matlab function中,在运行过程中出现如下问题Code generation for custom layer 'aten__linear0' for target 'mkldnn' is not supported as it returns a dlarra
classdef aten__linear0 < nnet.layer.Layer & nnet.layer.Formattable & ... nnet.layer.AutogeneratedFromPyTorch & nnet.lay...

6 months ago | 1 answer | 0

1

answer

Answered
在matlab function中导入net,但是出现了以下问题,尝试过6.3和8.1版本的MinG64,但是一直报错。Deep learning code generation using MinGW64 Compiler (C++) toolchain is not supported for mkldnn target.
我上传了文件并压缩了。我的matlab版本是2024a,python为3.8。而且我发现了如果我直接用net = importNetworkFromPyTorch(modelfile) 这段代码生成net的话plot(net)的架构是错误的。但是我如果我在...

6 months ago | 0

Answered
在matlab function中导入net,但是出现了以下问题,尝试过6.3和8.1版本的MinG64,但是一直报错。Deep learning code generation using MinGW64 Compiler (C++) toolchain is not supported for mkldnn target.
好的,谢谢。我还有一个问题。我发现我在pytorch中训练的模型通过net = importNetworkFromPyTorch(modelfile);导入到matlab后模型架构好像发生了变化。

7 months ago | 0