Created
December 14, 2016 13:46
-
-
Save dongzhuoyao/7793ed413d98a204bde43fd2387dbf6a to your computer and use it in GitHub Desktop.
deeplab-attention-to-scale
This file contains hidden or 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
| # VGG 16-layer network convolutional finetuning | |
| # Network modified to have smaller receptive field (128 pixels) | |
| # nand smaller stride (8 pixels) when run in convolutional mode. | |
| # | |
| # In this model we also change max pooling size in the first 4 layers | |
| # from 2 to 3 while retaining stride = 2 | |
| # which makes it easier to exactly align responses at different layers. | |
| # | |
| # For alignment to work, we set (we choose 32x so as to be able to evaluate | |
| # the model for all different subsampling sizes): | |
| # (1) input dimension equal to | |
| # $n = 32 * k - 31$, e.g., 321 (for k = 11) | |
| # Dimension after pooling w. subsampling: | |
| # (16 * k - 15); (8 * k - 7); (4 * k - 3); (2 * k - 1); (k). | |
| # For k = 11, these translate to | |
| # 161; 81; 41; 21; 11 | |
| # | |
| name: "deeplabv2_vgg16" | |
| layer { | |
| name: "data" | |
| type: "ImageSegData" | |
| top: "data" | |
| top: "label" | |
| top: "data_dim" | |
| include { | |
| phase: TRAIN | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 321 | |
| mean_value: 104.008 | |
| mean_value: 116.669 | |
| mean_value: 122.675 | |
| } | |
| image_data_param { | |
| root_folder: "/home/guest1/Documents/VOCdevkit/VOC2012" | |
| source: "voc12/list/train.txt" | |
| batch_size: 10 | |
| shuffle: true | |
| label_type: PIXEL | |
| } | |
| } | |
| ###################### DeepLab #################### | |
| layer { | |
| name: "conv1_1" | |
| type: "Convolution" | |
| bottom: "data" | |
| top: "conv1_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 64 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu1_1" | |
| type: "ReLU" | |
| bottom: "conv1_1" | |
| top: "conv1_1" | |
| } | |
| layer { | |
| name: "conv1_2" | |
| type: "Convolution" | |
| bottom: "conv1_1" | |
| top: "conv1_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 64 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu1_2" | |
| type: "ReLU" | |
| bottom: "conv1_2" | |
| top: "conv1_2" | |
| } | |
| layer { | |
| name: "pool1" | |
| type: "Pooling" | |
| bottom: "conv1_2" | |
| top: "pool1" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| pad: 1 | |
| } | |
| } | |
| layer { | |
| name: "conv2_1" | |
| type: "Convolution" | |
| bottom: "pool1" | |
| top: "conv2_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 128 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu2_1" | |
| type: "ReLU" | |
| bottom: "conv2_1" | |
| top: "conv2_1" | |
| } | |
| layer { | |
| name: "conv2_2" | |
| type: "Convolution" | |
| bottom: "conv2_1" | |
| top: "conv2_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 128 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu2_2" | |
| type: "ReLU" | |
| bottom: "conv2_2" | |
| top: "conv2_2" | |
| } | |
| layer { | |
| name: "pool2" | |
| type: "Pooling" | |
| bottom: "conv2_2" | |
| top: "pool2" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| pad: 1 | |
| } | |
| } | |
| layer { | |
| name: "conv3_1" | |
| type: "Convolution" | |
| bottom: "pool2" | |
| top: "conv3_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu3_1" | |
| type: "ReLU" | |
| bottom: "conv3_1" | |
| top: "conv3_1" | |
| } | |
| layer { | |
| name: "conv3_2" | |
| type: "Convolution" | |
| bottom: "conv3_1" | |
| top: "conv3_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu3_2" | |
| type: "ReLU" | |
| bottom: "conv3_2" | |
| top: "conv3_2" | |
| } | |
| layer { | |
| name: "conv3_3" | |
| type: "Convolution" | |
| bottom: "conv3_2" | |
| top: "conv3_3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu3_3" | |
| type: "ReLU" | |
| bottom: "conv3_3" | |
| top: "conv3_3" | |
| } | |
| layer { | |
| name: "pool3" | |
| type: "Pooling" | |
| bottom: "conv3_3" | |
| top: "pool3" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| pad: 1 | |
| } | |
| } | |
| layer { | |
| name: "conv4_1" | |
| type: "Convolution" | |
| bottom: "pool3" | |
| top: "conv4_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu4_1" | |
| type: "ReLU" | |
| bottom: "conv4_1" | |
| top: "conv4_1" | |
| } | |
| layer { | |
| name: "conv4_2" | |
| type: "Convolution" | |
| bottom: "conv4_1" | |
| top: "conv4_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu4_2" | |
| type: "ReLU" | |
| bottom: "conv4_2" | |
| top: "conv4_2" | |
| } | |
| layer { | |
| name: "conv4_3" | |
| type: "Convolution" | |
| bottom: "conv4_2" | |
| top: "conv4_3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu4_3" | |
| type: "ReLU" | |
| bottom: "conv4_3" | |
| top: "conv4_3" | |
| } | |
| layer { | |
| bottom: "conv4_3" | |
| top: "pool4" | |
| name: "pool4" | |
| type: "Pooling" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| pad: 1 | |
| stride: 1 | |
| } | |
| } | |
| layer { | |
| name: "conv5_1" | |
| type: "Convolution" | |
| bottom: "pool4" | |
| top: "conv5_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 2 | |
| kernel_size: 3 | |
| dilation: 2 | |
| } | |
| } | |
| layer { | |
| name: "relu5_1" | |
| type: "ReLU" | |
| bottom: "conv5_1" | |
| top: "conv5_1" | |
| } | |
| layer { | |
| name: "conv5_2" | |
| type: "Convolution" | |
| bottom: "conv5_1" | |
| top: "conv5_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 2 | |
| kernel_size: 3 | |
| dilation: 2 | |
| } | |
| } | |
| layer { | |
| name: "relu5_2" | |
| type: "ReLU" | |
| bottom: "conv5_2" | |
| top: "conv5_2" | |
| } | |
| layer { | |
| name: "conv5_3" | |
| type: "Convolution" | |
| bottom: "conv5_2" | |
| top: "conv5_3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 512 | |
| pad: 2 | |
| kernel_size: 3 | |
| dilation: 2 | |
| } | |
| } | |
| layer { | |
| name: "relu5_3" | |
| type: "ReLU" | |
| bottom: "conv5_3" | |
| top: "conv5_3" | |
| } | |
| layer { | |
| bottom: "conv5_3" | |
| top: "pool5" | |
| name: "pool5" | |
| type: "Pooling" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 1 | |
| pad: 1 | |
| } | |
| } | |
| ### hole = 6 | |
| layer { | |
| name: "fc6_1" | |
| type: "Convolution" | |
| bottom: "pool5" | |
| top: "fc6_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| pad: 6 | |
| kernel_size: 3 | |
| dilation: 6 | |
| } | |
| } | |
| layer { | |
| name: "relu6_1" | |
| type: "ReLU" | |
| bottom: "fc6_1" | |
| top: "fc6_1" | |
| } | |
| layer { | |
| name: "drop6_1" | |
| type: "Dropout" | |
| bottom: "fc6_1" | |
| top: "fc6_1" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc7_1" | |
| type: "Convolution" | |
| bottom: "fc6_1" | |
| top: "fc7_1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| kernel_size: 1 | |
| } | |
| } | |
| layer { | |
| name: "relu7_1" | |
| type: "ReLU" | |
| bottom: "fc7_1" | |
| top: "fc7_1" | |
| } | |
| layer { | |
| name: "drop7_1" | |
| type: "Dropout" | |
| bottom: "fc7_1" | |
| top: "fc7_1" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc8_voc12_1" | |
| type: "Convolution" | |
| bottom: "fc7_1" | |
| top: "fc8_voc12_1" | |
| param { | |
| lr_mult: 10 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 20 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 21 | |
| kernel_size: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| ### hole = 12 | |
| layer { | |
| name: "fc6_2" | |
| type: "Convolution" | |
| bottom: "pool5" | |
| top: "fc6_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| pad: 12 | |
| kernel_size: 3 | |
| dilation: 12 | |
| } | |
| } | |
| layer { | |
| name: "relu6_2" | |
| type: "ReLU" | |
| bottom: "fc6_2" | |
| top: "fc6_2" | |
| } | |
| layer { | |
| name: "drop6_2" | |
| type: "Dropout" | |
| bottom: "fc6_2" | |
| top: "fc6_2" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc7_2" | |
| type: "Convolution" | |
| bottom: "fc6_2" | |
| top: "fc7_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| kernel_size: 1 | |
| } | |
| } | |
| layer { | |
| name: "relu7_2" | |
| type: "ReLU" | |
| bottom: "fc7_2" | |
| top: "fc7_2" | |
| } | |
| layer { | |
| name: "drop7_2" | |
| type: "Dropout" | |
| bottom: "fc7_2" | |
| top: "fc7_2" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc8_voc12_2" | |
| type: "Convolution" | |
| bottom: "fc7_2" | |
| top: "fc8_voc12_2" | |
| param { | |
| lr_mult: 10 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 20 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 21 | |
| kernel_size: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| ### hole = 18 | |
| layer { | |
| name: "fc6_3" | |
| type: "Convolution" | |
| bottom: "pool5" | |
| top: "fc6_3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| pad: 18 | |
| kernel_size: 3 | |
| dilation: 18 | |
| } | |
| } | |
| layer { | |
| name: "relu6_3" | |
| type: "ReLU" | |
| bottom: "fc6_3" | |
| top: "fc6_3" | |
| } | |
| layer { | |
| name: "drop6_3" | |
| type: "Dropout" | |
| bottom: "fc6_3" | |
| top: "fc6_3" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc7_3" | |
| type: "Convolution" | |
| bottom: "fc6_3" | |
| top: "fc7_3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| kernel_size: 1 | |
| } | |
| } | |
| layer { | |
| name: "relu7_3" | |
| type: "ReLU" | |
| bottom: "fc7_3" | |
| top: "fc7_3" | |
| } | |
| layer { | |
| name: "drop7_3" | |
| type: "Dropout" | |
| bottom: "fc7_3" | |
| top: "fc7_3" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc8_voc12_3" | |
| type: "Convolution" | |
| bottom: "fc7_3" | |
| top: "fc8_voc12_3" | |
| param { | |
| lr_mult: 10 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 20 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 21 | |
| kernel_size: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| ### hole = 24 | |
| layer { | |
| name: "fc6_4" | |
| type: "Convolution" | |
| bottom: "pool5" | |
| top: "fc6_4" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| pad: 24 | |
| kernel_size: 3 | |
| dilation: 24 | |
| } | |
| } | |
| layer { | |
| name: "relu6_4" | |
| type: "ReLU" | |
| bottom: "fc6_4" | |
| top: "fc6_4" | |
| } | |
| layer { | |
| name: "drop6_4" | |
| type: "Dropout" | |
| bottom: "fc6_4" | |
| top: "fc6_4" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc7_4" | |
| type: "Convolution" | |
| bottom: "fc6_4" | |
| top: "fc7_4" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 1024 | |
| kernel_size: 1 | |
| } | |
| } | |
| layer { | |
| name: "relu7_4" | |
| type: "ReLU" | |
| bottom: "fc7_4" | |
| top: "fc7_4" | |
| } | |
| layer { | |
| name: "drop7_4" | |
| type: "Dropout" | |
| bottom: "fc7_4" | |
| top: "fc7_4" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "fc8_voc12_4" | |
| type: "Convolution" | |
| bottom: "fc7_4" | |
| top: "fc8_voc12_4" | |
| param { | |
| lr_mult: 10 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 20 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 21 | |
| kernel_size: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.01 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| ### SUM the four branches | |
| layer { | |
| bottom: "fc8_voc12_1" | |
| bottom: "fc8_voc12_2" | |
| bottom: "fc8_voc12_3" | |
| bottom: "fc8_voc12_4" | |
| top: "fc8_voc12" | |
| name: "fc8_voc12" | |
| type: "Eltwise" | |
| eltwise_param { | |
| operation: SUM | |
| } | |
| } | |
| ################# | |
| layer { | |
| bottom: "label" | |
| top: "label_shrink" | |
| name: "label_shrink" | |
| type: "Interp" | |
| interp_param { | |
| shrink_factor: 8 | |
| pad_beg: 0 | |
| pad_end: 0 | |
| } | |
| } | |
| layer { | |
| name: "loss" | |
| type: "SoftmaxWithLoss" | |
| bottom: "fc8_voc12" | |
| bottom: "label_shrink" | |
| include { | |
| phase: TRAIN | |
| } | |
| loss_param { | |
| ignore_label: 255 | |
| } | |
| } | |
| layer { | |
| name: "accuracy" | |
| type: "SegAccuracy" | |
| bottom: "fc8_voc12" | |
| bottom: "label_shrink" | |
| top: "accuracy" | |
| seg_accuracy_param { | |
| ignore_label: 255 | |
| } | |
| } | |
| layer { | |
| name: "silence" | |
| type: "Silence" | |
| bottom: "data_dim" | |
| } | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment