Created
July 12, 2018 22:11
-
-
Save Eric-mingjie/7f08a87ffb8c48d240d63e504fb81a38 to your computer and use it in GitHub Desktop.
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
| # @article{ThiNet_ICCV17, | |
| # Author = {Jian-Hao Luo, Jianxin Wu, and Weiyao Lin}, | |
| # Title = {ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression}, | |
| # Journal = {arXiv:1707.06342}, | |
| # Year = {2017} | |
| # } | |
| # fixed size: center 224x224 crop from resized image with 256x256 | |
| # The accuracy should be: Top-1: 0.6734, Top-5: 0.8792 | |
| # If you have any problem, please feel free to contact Jian-Hao Luo (luojh@lamda.nju.edu.cn). | |
| # 2017-07-29 | |
| layer { | |
| name: "data" | |
| type: "Data" | |
| top: "data" | |
| top: "label" | |
| include { | |
| phase: TRAIN | |
| } | |
| transform_param { | |
| mirror: true | |
| crop_size: 224 | |
| mean_value: 104 | |
| mean_value: 117 | |
| mean_value: 123 | |
| } | |
| data_param { | |
| source: "/opt/luojh/Dataset/ImageNet/lmdb/ilsvrc12_train_lmdb" | |
| batch_size: 32 | |
| backend: LMDB | |
| } | |
| } | |
| layer { | |
| name: "data" | |
| type: "Data" | |
| top: "data" | |
| top: "label" | |
| include { | |
| phase: TEST | |
| } | |
| transform_param { | |
| mirror: false | |
| crop_size: 224 | |
| mean_value: 104 | |
| mean_value: 117 | |
| mean_value: 123 | |
| } | |
| data_param { | |
| source: "/opt/luojh/Dataset/ImageNet/lmdb/ilsvrc12_val_lmdb" | |
| batch_size: 50 | |
| backend: LMDB | |
| } | |
| } | |
| 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: 32 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu1_1" | |
| type: "ReLU" | |
| bottom: "conv1_1" | |
| top: "relu1_1" | |
| } | |
| layer { | |
| name: "conv1_2" | |
| type: "Convolution" | |
| bottom: "relu1_1" | |
| top: "conv1_2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 32 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu1_2" | |
| type: "ReLU" | |
| bottom: "conv1_2" | |
| top: "relu1_2" | |
| } | |
| layer { | |
| name: "pool1" | |
| type: "Pooling" | |
| bottom: "relu1_2" | |
| top: "pool1" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| 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: 64 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu2_1" | |
| type: "ReLU" | |
| bottom: "conv2_1" | |
| top: "relu2_1" | |
| } | |
| layer { | |
| name: "conv2_2" | |
| type: "Convolution" | |
| bottom: "relu2_1" | |
| top: "conv2_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: "relu2_2" | |
| type: "ReLU" | |
| bottom: "conv2_2" | |
| top: "relu2_2" | |
| } | |
| layer { | |
| name: "pool2" | |
| type: "Pooling" | |
| bottom: "relu2_2" | |
| top: "pool2" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| 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: 128 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu3_1" | |
| type: "ReLU" | |
| bottom: "conv3_1" | |
| top: "relu3_1" | |
| } | |
| layer { | |
| name: "conv3_2" | |
| type: "Convolution" | |
| bottom: "relu3_1" | |
| top: "conv3_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: "relu3_2" | |
| type: "ReLU" | |
| bottom: "conv3_2" | |
| top: "relu3_2" | |
| } | |
| layer { | |
| name: "conv3_3" | |
| type: "Convolution" | |
| bottom: "relu3_2" | |
| top: "conv3_3" | |
| 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: "relu3_3" | |
| type: "ReLU" | |
| bottom: "conv3_3" | |
| top: "relu3_3" | |
| } | |
| layer { | |
| name: "pool3" | |
| type: "Pooling" | |
| bottom: "relu3_3" | |
| top: "pool3" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| 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: 256 | |
| pad: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu4_1" | |
| type: "ReLU" | |
| bottom: "conv4_1" | |
| top: "relu4_1" | |
| } | |
| layer { | |
| name: "conv4_2" | |
| type: "Convolution" | |
| bottom: "relu4_1" | |
| top: "conv4_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: "relu4_2" | |
| type: "ReLU" | |
| bottom: "conv4_2" | |
| top: "relu4_2" | |
| } | |
| layer { | |
| name: "conv4_3" | |
| type: "Convolution" | |
| bottom: "relu4_2" | |
| top: "conv4_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: "relu4_3" | |
| type: "ReLU" | |
| bottom: "conv4_3" | |
| top: "relu4_3" | |
| } | |
| layer { | |
| name: "pool4" | |
| type: "Pooling" | |
| bottom: "relu4_3" | |
| top: "pool4" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 2 | |
| stride: 2 | |
| } | |
| } | |
| 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: 1 | |
| kernel_size: 3 | |
| } | |
| } | |
| layer { | |
| name: "relu5_1" | |
| type: "ReLU" | |
| bottom: "conv5_1" | |
| top: "relu5_1" | |
| } | |
| layer { | |
| name: "conv5_2" | |
| type: "Convolution" | |
| bottom: "relu5_1" | |
| top: "conv5_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: "relu5_2" | |
| type: "ReLU" | |
| bottom: "conv5_2" | |
| top: "relu5_2" | |
| } | |
| layer { | |
| name: "conv5_3" | |
| type: "Convolution" | |
| bottom: "relu5_2" | |
| top: "conv5_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: "relu5_3" | |
| type: "ReLU" | |
| bottom: "conv5_3" | |
| top: "relu5_3" | |
| } | |
| layer { | |
| name: "pool5" | |
| type: "Pooling" | |
| bottom: "relu5_3" | |
| top: "pool5" | |
| pooling_param { | |
| pool: AVE | |
| kernel_size: 14 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "softmax" | |
| type: "InnerProduct" | |
| bottom: "pool5" | |
| top: "softmax" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| inner_product_param { | |
| num_output: 1000 | |
| } | |
| } | |
| layer { | |
| name: "loss" | |
| type: "SoftmaxWithLoss" | |
| bottom: "softmax" | |
| bottom: "label" | |
| top: "loss" | |
| } | |
| layer { | |
| name: "acc_top_1" | |
| type: "Accuracy" | |
| bottom: "softmax" | |
| bottom: "label" | |
| top: "acc_top_1" | |
| accuracy_param { | |
| top_k: 1 | |
| } | |
| } | |
| layer { | |
| name: "acc_top_5" | |
| type: "Accuracy" | |
| bottom: "softmax" | |
| bottom: "label" | |
| top: "acc_top_5" | |
| accuracy_param { | |
| top_k: 5 | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment