improving channelnet with inverted residual blocks
RamsleyJunting opened this issue · comments
I‘ve read your paper, it's a nice work. I notice you mention MobileNet_v2 in your paper, but in the comparison between ChannelNet-v1 and other CNNs in terms of the top-1 accuracy on the ImageNet validation set, it isn't include the result of mobilenet_v2. I wonder if you have the plan to improve channelnet with inverted residual block based on mobilenet_v2?
Hi,
Thanks for your appreciation. This work was finished by Dec 2017. At that
time, mobilenetv2 was not published. So we test our methods based on
Mobilenetv1. But since our method is orthogonal to both of them, we mention
V2 in our paper for clarification. Currently we don't have plan to migrate
it to V2 because I am working on a new project. If you are interested, I
would like to provide any help I can. Thank you.
On Wed, Sep 19, 2018, 05:36 Ramsley ***@***.***> wrote:
I‘ve read your paper, it's a nice work. I notice you mention MobileNet_v2
in your paper, but in the comparison between ChannelNet-v1 and other CNNs
in terms of the top-1 accuracy on the ImageNet validation set, it isn't
include the result of mobilenet_v2. I wonder if you have the plan to
improve channelnet with inverted residual block based on mobilenet_v2?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#2>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/AGGcr15IhTf3uGf7s1ibklj3borZvArdks5uch4UgaJpZM4Wv4cG>
.
--
Hongyang