Last active
June 21, 2019 13:28
-
-
Save ashutoshsatapathy1990/2b69006b0866418e4556bc8d3ae7ecb0 to your computer and use it in GitHub Desktop.
VGG-19 enables with batch normalization layer after each convolution layer
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
| #VGGNet19-BN | |
| name: "VGGNet19" | |
| layer { | |
| name: "train-data" | |
| type: "Data" | |
| top: "data" | |
| top: "label" | |
| transform_param { | |
| mirror: true | |
| crop_size: 224 | |
| } | |
| data_param { | |
| batch_size: 32 | |
| } | |
| include { stage: "train" } | |
| } | |
| layer { | |
| name: "val-data" | |
| type: "Data" | |
| top: "data" | |
| top: "label" | |
| transform_param { | |
| mirror: false | |
| crop_size: 224 | |
| } | |
| data_param { | |
| batch_size: 16 | |
| } | |
| include { stage: "val" } | |
| } | |
| layer { | |
| bottom:"data" | |
| top:"conv1_1" | |
| name:"conv1_1" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:64 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv1_1" | |
| name: "conv1_1/bn" | |
| top: "conv1_1/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv1_1/bn" | |
| top:"conv1_1/bn" | |
| name:"relu1_1" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv1_1/bn" | |
| top:"conv1_2" | |
| name:"conv1_2" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:64 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv1_2" | |
| name: "conv1_2/bn" | |
| top: "conv1_2/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv1_2/bn" | |
| top:"conv1_2/bn" | |
| name:"relu1_2" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv1_2/bn" | |
| top:"pool1" | |
| name:"pool1" | |
| type:"Pooling" | |
| pooling_param { | |
| pool:MAX | |
| kernel_size:2 | |
| stride:2 | |
| } | |
| } | |
| layer { | |
| bottom:"pool1" | |
| top:"conv2_1" | |
| name:"conv2_1" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:128 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv2_1" | |
| name: "conv2_1/bn" | |
| top: "conv2_1/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv2_1/bn" | |
| top:"conv2_1/bn" | |
| name:"relu2_1" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv2_1/bn" | |
| top:"conv2_2" | |
| name:"conv2_2" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:128 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv2_2" | |
| name: "conv2_2/bn" | |
| top: "conv2_2/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv2_2/bn" | |
| top:"conv2_2/bn" | |
| name:"relu2_2" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv2_2/bn" | |
| top:"pool2" | |
| name:"pool2" | |
| type:"Pooling" | |
| pooling_param { | |
| pool:MAX | |
| kernel_size:2 | |
| stride:2 | |
| } | |
| } | |
| layer { | |
| bottom:"pool2" | |
| top:"conv3_1" | |
| name: "conv3_1" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:256 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv3_1" | |
| name: "conv3_1/bn" | |
| top: "conv3_1/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv3_1/bn" | |
| top:"conv3_1/bn" | |
| name:"relu3_1" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv3_1/bn" | |
| top:"conv3_2" | |
| name:"conv3_2" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:256 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv3_2" | |
| name: "conv3_2/bn" | |
| top: "conv3_2/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv3_2/bn" | |
| top:"conv3_2/bn" | |
| name:"relu3_2" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv3_2/bn" | |
| top:"conv3_3" | |
| name:"conv3_3" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:256 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv3_3" | |
| name: "conv3_3/bn" | |
| top: "conv3_3/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv3_3/bn" | |
| top:"conv3_3/bn" | |
| name:"relu3_3" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv3_3/bn" | |
| top:"conv3_4" | |
| name:"conv3_4" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output:256 | |
| pad:1 | |
| kernel_size:3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv3_4" | |
| name: "conv3_4/bn" | |
| top: "conv3_4/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv3_4/bn" | |
| top:"conv3_4/bn" | |
| name:"relu3_4" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv3_4/bn" | |
| top:"pool3" | |
| name:"pool3" | |
| type:"Pooling" | |
| pooling_param { | |
| pool:MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| bottom:"pool3" | |
| top:"conv4_1" | |
| name:"conv4_1" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv4_1" | |
| name: "conv4_1/bn" | |
| top: "conv4_1/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv4_1/bn" | |
| top:"conv4_1/bn" | |
| name:"relu4_1" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv4_1/bn" | |
| top:"conv4_2" | |
| name:"conv4_2" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv4_2" | |
| name: "conv4_2/bn" | |
| top: "conv4_2/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv4_2/bn" | |
| top:"conv4_2/bn" | |
| name:"relu4_2" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv4_2/bn" | |
| top:"conv4_3" | |
| name:"conv4_3" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv4_3" | |
| name: "conv4_3/bn" | |
| top: "conv4_3/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv4_3/bn" | |
| top:"conv4_3/bn" | |
| name:"relu4_3" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv4_3/bn" | |
| top:"conv4_4" | |
| name:"conv4_4" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv4_4" | |
| name: "conv4_4/bn" | |
| top: "conv4_4/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv4_4/bn" | |
| top:"conv4_4/bn" | |
| name:"relu4_4" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv4_4/bn" | |
| top:"pool4" | |
| name:"pool4" | |
| type:"Pooling" | |
| pooling_param { | |
| pool:MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| bottom:"pool4" | |
| top:"conv5_1" | |
| name:"conv5_1" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv5_1" | |
| name: "conv5_1/bn" | |
| top: "conv5_1/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv5_1/bn" | |
| top:"conv5_1/bn" | |
| name:"relu5_1" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv5_1/bn" | |
| top:"conv5_2" | |
| name:"conv5_2" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv5_2" | |
| name: "conv5_2/bn" | |
| top: "conv5_2/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv5_2/bn" | |
| top:"conv5_2/bn" | |
| name:"relu5_2" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv5_2/bn" | |
| top:"conv5_3" | |
| name:"conv5_3" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv5_3" | |
| name: "conv5_3/bn" | |
| top: "conv5_3/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv5_3/bn" | |
| top:"conv5_3/bn" | |
| name:"relu5_3" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv5_3/bn" | |
| top:"conv5_4" | |
| name:"conv5_4" | |
| type:"Convolution" | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom: "conv5_4" | |
| name: "conv5_4/bn" | |
| top: "conv5_4/bn" | |
| type: "BatchNorm" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 0 | |
| } | |
| batch_norm_param { | |
| scale_filler { | |
| type: "constant" | |
| value: 1 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| bottom:"conv5_4/bn" | |
| top:"conv5_4/bn" | |
| name:"relu5_4" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"conv5_4/bn" | |
| top:"pool5" | |
| name:"pool5" | |
| type:"Pooling" | |
| pooling_param { | |
| pool:MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| bottom:"pool5" | |
| top:"fc6" | |
| name:"fc6" | |
| type:"InnerProduct" | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom:"fc6" | |
| top:"fc6" | |
| name:"relu6" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"fc6" | |
| top:"fc6" | |
| name:"drop6" | |
| type:"Dropout" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| bottom:"fc6" | |
| top:"fc7" | |
| name:"fc7" | |
| type:"InnerProduct" | |
| inner_product_param { | |
| num_output: 4096 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| bottom:"fc7" | |
| top:"fc7" | |
| name:"relu7" | |
| type:"ReLU" | |
| } | |
| layer { | |
| bottom:"fc7" | |
| top:"fc7" | |
| name:"drop7" | |
| type:"Dropout" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| bottom:"fc7" | |
| top:"fc8" | |
| name:"fc8" | |
| type:"InnerProduct" | |
| inner_product_param { | |
| #num_output: 0 | |
| weight_filler { | |
| type: "msra" | |
| std: 0.0005 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| } | |
| layer { | |
| name: "accuracy" | |
| type: "Accuracy" | |
| bottom: "fc8" | |
| bottom: "label" | |
| top: "accuracy" | |
| include { stage: "val" } | |
| } | |
| layer { | |
| name: "loss" | |
| type: "SoftmaxWithLoss" | |
| bottom: "fc8" | |
| bottom: "label" | |
| top: "loss" | |
| exclude { stage: "deploy" } | |
| } | |
| layer { | |
| name: "softmax" | |
| type: "Softmax" | |
| bottom: "fc8" | |
| top: "softmax" | |
| include { stage: "deploy" } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment