The VGG model accept a 3-channel RGB image as input, but my data are single gray images, any suggestions for how to utilize the weights in first conv layer of VGG model?
Asked
Active
Viewed 1,620 times
1 Answers
1
So your filters in the first layer are of size w x h x 3 (for VGG, w=h=3), I'd suggest taking the mean over the last dimension and using them as w x h x 1. As you've probably figured out, you won't need to change any other weights.
This is inspired from a similar approach people have applied to initializing the VGG Imagenet model on flow images.
https://arxiv.org/pdf/1507.02159v1.pdf (Secion 2.2)

Amlan Kar
- 34
- 2