You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/07/04 21:47:39 UTC
[GitHub] ThomasDelteil commented on issue #8531: How to get the correlation
result of two feature maps?
ThomasDelteil commented on issue #8531: How to get the correlation result of two feature maps?
URL: https://github.com/apache/incubator-mxnet/issues/8531#issuecomment-402563556
@squidszyd
You can do the following:
```
C = 64
F1 = mx.nd.ones((1,C,10,10))
F2 = mx.nd.ones((1,C,3,3))
convolution = mx.gluon.nn.Conv2D(channels=1, kernel_size=(3,3), use_bias=False)
convolution.initialize(mx.init.Constant(F2))
out = convolution(F1)
print(out.shape)
```
```
(1, 1, 8, 8)
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services