pytorch-retinanet icon indicating copy to clipboard operation
pytorch-retinanet copied to clipboard

Changing the base network (to VGG, ResNet, DenseNet, etc.)

Open mubastan opened this issue 7 years ago • 0 comments

It will be nice to be able to train using other standard networks as well, since FPN requires too much memory. Right now, changing the base network in retinanet.py (e.g., to VGG) does not work out of the box.

Has anybody tried and got it working?

mubastan avatar Sep 03 '17 09:09 mubastan