Hi,
I want to convert the FC layers in the VGG-16 model to a CONV layers while keeping and using the pretrained weights. How should I act on this?
Thanks,
Saeed
Hi,
I want to convert the FC layers in the VGG-16 model to a CONV layers while keeping and using the pretrained weights. How should I act on this?
Thanks,
Saeed
Hi, you mean how to convert fc weights to conv kernel’s weight? if so I did like below.
fc_net.conv.load_state_dict({"weight": resnet.fc.state_dict()["weight"].view(1000, 2048, 1, 1),
"bias": resnet.fc.state_dict()["bias"]})
Great,
Will give it a try.
Thanks