resnet

Hello! In the Torch version of Bottleneck, it appears that self.dropblock2 is never used.

self.dropblock2 is initialized in lines 52-56 if radix == 1:
https://github.com/zhanghang1989/ResNeSt/blob/master/resnest/torch/resnet.py#L52-L56

        if dropblock_prob > 0.0:
            self.dropblock1 = DropBlock2D(dropblock_prob, 3)
            if radix == 1:
                self.d

Hi
when I do classification with the pretrained vggface2 model, how do I match a probability to a name? do you have a list of labels for the trained model?

Thanks

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!

loss = F.binary_cross_entropy_with_logits(
pred, label, weight=class_weight, reduction='none')

it should be modified for “loss = F.binary_cross_entropy_with_logits( pred, label, pos_weight=class_weight, reduction='none')

def binary_cross_entropy(pred,
                         label,
                         weight=None,
                         reduction='mean',