Closed ArtyZe closed 5 years ago
Could you give detailed descriptions for your problem, e.g., network configuration, task, input?
Thanks. Now I have solved the problem, but I have still some questions:
Besides residual architectures, we also tested it on the non-residual backbones in the paper. We presented one solution while the blocks can be implemented in a flexible manner (e.g., in the extension https://arxiv.org/pdf/1709.01507.pdf). Besides with/without biases, you can also try to add BatchNorm at the fc layers which we found work well on several backbone architectures.
Hello,
I am facing the same issue, most of the scales are 0.5, how could you solve it @ArtyZe ? The halves mean the output is zeros so the sigmoid ouput haves which is wired, @lishen-shirley @hujie-frank Do you suggest any solutions or tricks?
I am integrating the SE-block on Resnet50.
Thanks in advance
hello, @hujie-frank ,thanks for your great job. But when I use se module after a normal conv layer, all the scale value regress to 0.65, are not different so obviously like in your paper, do you have any ideas? Thanks