You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project is obsoleted and the development is merged into our ICCV 2021 work Zen-NAS. The new Github repository is https://github.com/idstcv/ZenNAS.
Can you please support choosing the number of channels? I have 1 channel input.
EfficientNet allows you to specify the number of input channels, for example if the image is grayscale.
https://github.com/lukemelas/EfficientNet-PyTorch/blob/master/efficientnet_pytorch/model.py#L321
in_channels is 3 by default but can be set to one.
The text was updated successfully, but these errors were encountered: