search

hfawaz / ijcnn19attacks

Adversarial Attacks on Deep Neural Networks for Time Series Classification
https://germain-forestier.info/src/ijcnn2019/
GNU General Public License v3.0
71 stars 28 forks source link

tsc_tutorial_keras_tf dimension problem #3

Open ulkursln opened 4 years ago

ulkursln commented 4 years ago

Hi,

I am trying to run "attack fsm". I guess you suppose that timeseries is univariate. Because the shape of timeseries I used was (#timestemps, #length_of_timestemps, #dimension) and it throws an error at the "adv = adv.reshape(adv.shape[0],adv.shape[1])" line. In fact, I could not get the underlying reason to reshape data with the same dimensions. what do you think, is it easy to make the app to run with multivariate data?

hfawaz commented 4 years ago

Hi,

Indeed we are working on multivariate data and will keep you up to date.