MATLAB Answers

onnx export issue with the average image

2 views (last 30 days)
michael scheinfeild
michael scheinfeild on 17 Apr 2019
Edited: michael scheinfeild on 17 Apr 2019
hi i export alexnet from matlab with onnx , but i dont have same features at layers so i checked the average image.
as i see there is issue with the average image.
i tried to import the network to c++(it passed some process use python cntk to dnn) and tested with all inputs zeros but i see with subtruction layer we have not same average image !
% convnet is alexnet
AverageImage=convnet.Layers(1).AverageImage;
figure,imagesc(AverageImage(:,:,1))
while in c++ output of layer data_Sub (first subtruction layer) . when all inputs are zero i suppose it should be the negative of the average .
Capture.JPG
i also check the channels and the values if there was some mix in rgb or some rotation but there is nothing clear here.
also as i see with other frameworks( tensorflow ..) and other netwroks vgg,googlnet
there is diffrence in implementation of the deep learning net . so i dont see way to have same featurs in matlab and python and c++ . only to retrain on the images in python or c++ .

  0 Comments

Sign in to comment.

Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!