Created
January 19, 2015 14:03
-
-
Save erogol/7618fb7cda696236932f to your computer and use it in GitHub Desktop.
maxout layer implementation for caffe library
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| layers { | |
| name: "conv1A" | |
| type: CONVOLUTION | |
| bottom: "data" | |
| top: "conv1A" | |
| blobs_lr: 1 | |
| blobs_lr: 2 | |
| weight_decay: 1 | |
| weight_decay: 0 | |
| convolution_param { | |
| num_output: 48 | |
| kernel_size: 9 | |
| stride: 1 | |
| } | |
| } | |
| layers { | |
| name: "conv1B" | |
| type: CONVOLUTION | |
| bottom: "data" | |
| top: "conv1B" | |
| blobs_lr: 1 | |
| blobs_lr: 2 | |
| weight_decay: 1 | |
| weight_decay: 0 | |
| convolution_param { | |
| num_output: 48 | |
| kernel_size: 9 | |
| stride: 1 | |
| } | |
| } | |
| layers { | |
| name: "maxout1" | |
| type: ELTWISE | |
| bottom: "conv1A" | |
| bottom: "conv1B" | |
| top: "maxout1" | |
| eltwise_param { | |
| operation:MAX | |
| } | |
| } |
Have you tested this code?Can it run?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I'm very new to Caffe but want to add a maxout layer in Nvidia DIGITS. I'm wondering about the "layers" keyword - haven't seen it before. At this Caffe tutorial page they only seem to use the "layer" keyword:
http://caffe.berkeleyvision.org/tutorial/layers.html