Skip to content
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

Support different number of input channels to YOLOX backbone #1239

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Support different number of input channels to YOLOX backbone #1239

wants to merge 3 commits into from

Commits on Apr 13, 2022

  1. Support different number of input channels to YOLOX backbone 

    Allow for arbitrary number of input channels to the YOLOX neural network. Previously, number of input channels were hardcoded to 3 (i.e. RGB only).
    @weiji14
    weiji14 committed Apr 13, 2022
    Configuration menu
    Copy the full SHA
    44c2f31 View commit details
    Browse the repository at this point in the history

Commits on Apr 14, 2022

  1. Set number of backbone_in_channels for yolox_nano model

    @weiji14
    weiji14 committed Apr 14, 2022
    Configuration menu
    Copy the full SHA
    d264836 View commit details
    Browse the repository at this point in the history

  2. Raise error when loading pretrained model with different i/o channels

    @weiji14
    weiji14 committed Apr 14, 2022
    Configuration menu
    Copy the full SHA
    4e42e61 View commit details
    Browse the repository at this point in the history