VGG classifier setting different from Original paper

[lichengunc]

One of the dropout layer was "wrongly" inserted.
The original final layers of Caffe Version (https://gist.github.com/ksimonyan/211839e770f7b538e2d8) is:
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout()
nn.Linear(4096, 1000),
)
This won't make difference when we use model.eval(), but will make discrepancy if we want to finetune VggNet by loading Caffe's parameters.

[colesbury]

Thanks for catching this. I'll fix this and retrain the VGG models.

…

On Fri, Mar 10, 2017 at 1:44 AM Licheng Yu ***@***.***> wrote: One of the dropout layer was "wrongly" inserted. The original final layers of Caffe Version ( https://gist.github.com/ksimonyan/211839e770f7b538e2d8) is: self.classifier = nn.Sequential( nn.Linear(512 * 7 * 7, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, 4096), nn.ReLU(True), nn.Dropout() nn.Linear(4096, 1000), ) This won't make difference when we use model.eval(), but will make discrepancy if we want to finetune VggNet by loading Caffe's parameters. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#92>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAoB-mQoAanKtu7ZOeBuY48ynFDezv_0ks5rkPFjgaJpZM4MZB_2> .