New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add better documentation for how to convert train/val nets into all-in-one nets #1192

Open

lukeyeager opened this issue Oct 20, 2016 · 1 comment

Labels

caffe documentation

Member

lukeyeager commented Oct 20, 2016 •

edited

Loading

Try to adjust the last layers in your network to look something like this.

For more information, here is how I've proposed updating Caffe's example networks to all-in-one nets, and here is how I updated the default DIGITS networks to be all-in-one nets.

http://stackoverflow.com/q/40143901/2404152

lukeyeager added caffe documentation labels

lukeyeager mentioned this issue

Infer one image "IndexError: too many indices for array" #1381

Open

lukeyeager mentioned this issue

ERROR: Your deploy network is missing a Softmax layer! #1439

Closed

Member Author

lukeyeager commented Feb 7, 2017

Once you know which layers need to be added, this chart is useful for figuring out how to select the phase/stage of each layer: #628 (comment)

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