-
Hi
Do you think it's possible to replace only GroupNorm part with MABN and the according Conv with CenConv, the rest of well-pretrained Conv+Bn remaining the same? I followed this kind of setting to …
-
Hi， thanks for your sharing，and I think your work is focus on efficiency Convolution Compute，Would you test one MoblieNet or ShuffleNet with your method？
-
I just want to train MobileNet with larger images but I have to put an Input tensor to the function otherwise it will stuck in this line.
https://github.com/keras-team/keras-applications/blob/maste…
-
As I know, its offical name is MobileNets. So in the ReadMe.md, could you guys fix it😃
Or use MobileNetV2？
-
Before you open an issue, please make sure you have tried the following steps:
1. Make sure your **environment** is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement…
-
If I want to use mobilenet as an encoder, which layers would you suggest?
In VGG16, you use 3rd, 4th, 5th maxpooling layers, If I want to use mobilenet, which layers should I choose?
-
how to change the two super-parameters ?and, why the train time of depth-wise convolution is longer than the same out number of convolution?