Feature map size co...
 
Notifications
Clear all

Feature map size constraints

1 Posts
1 Users
0 Likes
808 Views
0
Topic starter

Is there feature map size limitation for convolution snn?

This topic was modified 8 months ago 2 times by marvinfan
1 Answer
0
Topic starter

Yes. The maximum output feature map size supported by each core is 64 x 64, while our maximum input shape is 128 x 128. So you need to at least down-sample the input into 64 x 64 by pooling or stride-convolution in the first layer of your model.

Share:
Close
Back To