search

alexgkendall / SegNet-Tutorial

Files for a tutorial to train SegNet for road scenes using the CamVid dataset
http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
847 stars 517 forks source link

Question | how to Unsupervised Train SegNet? #36

Open MahmoudElkhateeb opened 8 years ago

MahmoudElkhateeb commented 8 years ago

Hi @alexgkendall

I want to Unsupervised Train SegNet with unlabeled data then fine-tune it with labeled data.

I want to remove the soft_max layer at the end of the network, and make the back-propagate via get the difference in distance between the input data and itself.

How simply make that using the current model of SegNet?

alexgkendall commented 8 years ago

Hey - you could add a Euclidean Loss regression layer at the end of the network, and feed in the output from the last decoder and the original input image?

etienne87 commented 8 years ago

I think you might want to normalize the pixels in [0,1]. See for example (https://github.com/mikesj-public/convolutional_autoencoder/blob/master/mnist_conv_autoencode.py).

arushk1 commented 8 years ago

@MahmoudElkhateeb Were you able to unsupervised train it?