how to extract features from layer 43 (RELU)-vgg19 about deep-goggle

[NerminSalem]

also another question when i extracted features of end layer using vgg19 it took more than 6 hours to reach a convergence, while when using alexnet end layer it gave more accurate results in almost 20 mins?
vgg19 suppose to give error rate less than that of alexnet, shouldn't that mean a better features representation?
sorry if i had soo many questions but yr work is really interesting

[aravindhm]

Did you truncate the network in the same way
net.layers = net.layers(1:end-3) ?

As for VGG-19 being very slow, it is because of the network is massive and each forward pass takes much longer than for alexnet. Also, the hyperparameters were tuned for Alexnet. If you want to play with VGG-19 it might be better to use the code here - https://github.com/aravindhm/nnpreimage.

[NerminSalem]

yes it worked, thanks alot for your help and support
will check the link you provide, i understand the process much better now