What is pretrained-model? about facex-zoo HOT 5 OPEN

SOTA backbones model : models which are trained by the SOTA backbones with the same head, i.e. MV-Softmax.
SOTA heads model : models which are trained by the SOTA heads with the same backbone, i.e. MobileFaceNet.

from facex-zoo.

@wang21jun I got it!
Thank you for your clear answer.

from facex-zoo.

If I just want to train head, not re-train the backbone in my custom dataset. How can i solve it?

from facex-zoo.

If I just want to train head, not re-train the backbone in my custom dataset. How can i solve it?

You can search keyword freezing backbone pytorch.
Specifically, you can set requires_grad = False for the whole learnable parameters of the backbone. But the easiest way is just putting the parameters of head into the optimizer but not the params of backbone.

from facex-zoo.

@vietth-bka thank you!

from facex-zoo.