Caffe for feed forward networks -


has experience using caffe feed forward network instead of convolutional neural network?

my input data 1 dimensional. ok, when want use layers max pooling, caffe assumes square shaped kernel size. rather need 1 dim max pooling kernel.

found it:

layer {   name: "pool1"   type: "pooling"   bottom: "ip1"   top: "pool1"   pooling_param {     pool: max     kernel_h: 3     kernel_w: 1    } } 

Comments

Popular posts from this blog

gcc - MinGW's ld cannot perform PE operations on non PE output file -

timeout - Handshake_timeout on RabbitMQ using python and pika from remote vm -

c# - Search and Add Comment with OpenXML for Word -