shelhamer/readme.md Secret

Last active August 10, 2017 10:42

Star () You must be signed in to star a gist
Fork () You must be signed in to fork a gist

Learn more about clone URLs
Clone this repository at <script src="https://gist.github.com/shelhamer/91eece041c19ff8968ee.js"></script>
Save shelhamer/91eece041c19ff8968ee to your computer and use it in GitHub Desktop.

Download ZIP

FCN-8s Fully Convolutional Semantic Segmentation on PASCAL-Context

Raw

See the reference implementation at http://fcn.berkeleyvision.org. This pre-release is deprecated.

arasharchor commented Mar 11, 2016

@shelhamer I want to fine tune fcn8 on a different dataset for predicting flow magnitude map which is gray scale image by doing regression by changing the loss to euclidean and num_outputs of last layer to 1. is that right?
The loss is too high. basically for how many iterations should I set it in this case?
should I first do some changes in solver around your parameters or in this case I should decrease e.g. base_lr because now we are finetuning.

thanks a lot for your help

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment