Implement flatten layer in CNN

Please, how to implement the flatten layer in CNN, i.e. transform 2D feature map of convoulution layer output to 1D vector?

[Mohammad Sami]

MATLAB R2019a introduced flatten layer. Which version are you using.

https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.flattenlayer.html

[Ali Al-Saegh]

I am using MATLAB 2019a, the availabe flatten layer is used for sequence data. I do not know wheather it is possible to use it for transforming 2D features to a 1D vector.

[Mohammad Sami]

You should be able to put a fully connected layer after a convolutional layer. This will essentially flatten as well.

[Ali Al-Saegh]

I was thinking about this but it is actually confusing me as it is just a fully connected, I understand it as connecting each entry within a feature map to all of the neurons in the fully connected layer.

I still cannot imagine how a fully connected layer flattens a feature map!

Thanks for your help!

[Jianyu Zhao]

Hi friend, I also met this problem, I tried flatten layer but I found it is used for squence data. So have you solved this problem? Or do you have any ideas? I don't know how to do it so I just jump into pytorch instead:(