about this function:_make_divisible()

[lixiangwang]

Hi!!!
What does this function do? ---->>_make_divisible(), Both channels and exp_size are processed by this function， why? It seems that the original paper did not mention？

[Andy1621]

It is used to make sure that the number channel can be divide by 8（for example）. You can see it in MobileNetV2.

[AishuaiYao]

都是中国人，不能用汉语交流吗:-D

[AishuaiYao]

It is used to make sure that the number channel can be divide by 8（for example）. You can see it in MobileNetV2.

哪里说过

[Andy1621]

It is used to make sure that the number channel can be divide by 8（for example）. You can see it in MobileNetV2.

哪里说过

https://github.com/d-li14/mobilenetv2.pytorch/blob/master/models/imagenet/mobilenetv2.py

 This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8

[AishuaiYao]

It is used to make sure that the number channel can be divide by 8（for example）. You can see it in MobileNetV2.

哪里说过

https://github.com/d-li14/mobilenetv2.pytorch/blob/master/models/imagenet/mobilenetv2.py

 This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8

通过这个操作，在占用空间和精度上做调节，我理解的对吗

[Andy1621]

@AishuaiYao 他的意思是放缩网络宽度保证channel数被8整除，被8整除可能有点玄学，个人觉得与计算机底层01有关，毕竟现在所有网络的channel都是2的倍数

[461233373]

都是中国人，不能用汉语交流吗:-D

骚得一批