Skip to content
This repository has been archived by the owner on Jan 24, 2024. It is now read-only.

Convolution层only support group == 1? #477

Open
whongjob opened this issue Nov 7, 2018 · 0 comments
Open

Convolution层only support group == 1? #477

whongjob opened this issue Nov 7, 2018 · 0 comments

Comments

@whongjob
Copy link

whongjob commented Nov 7, 2018

问题:
在x86上执行net_executer.prediction()的时候中断报错: x86_utils.h:906] Check failed:group == 1 (32 == 1) only support group == 1
*** Check failed:group == 1 (32 == 1) fatal error stack trace: ***:

我用的MobileNet-SSD模型,卷积层如下:
layer {
name: "conv1/dw"
type: "Convolution"
bottom: "conv0"
top: "conv1/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 32
bias_term: false
pad: 1
kernel_size: 3
group: 32
#engine: CAFFE
weight_filler {
type: "msra"
}
}
}
是x86上只支持group==1?我把这层换成ConvolutionDepthwise也没用。

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant