Created
September 9, 2015 12:45
-
-
Save mfigurnov/4736f2f4a6e1676d074d to your computer and use it in GitHub Desktop.
CIFAR-10 Network in Network with fix for cuDNN
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
| net: "train_val.prototxt" | |
| test_iter: 100 | |
| test_interval: 500 | |
| base_lr: 0.1 | |
| momentum: 0.9 | |
| weight_decay: 0.0001 | |
| lr_policy: "step" | |
| gamma: 0.1 | |
| stepsize: 100000 | |
| display: 100 | |
| max_iter: 120000 | |
| snapshot: 10000 | |
| snapshot_prefix: "cifar10_nin" | |
| solver_mode: GPU |
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
| name: "CIFAR10_full" | |
| layer { | |
| name: "cifar" | |
| type: "HDF5Data" | |
| top: "data" | |
| top: "label" | |
| include { | |
| phase: TRAIN | |
| } | |
| hdf5_data_param { | |
| source: "../cifar-train.txt" | |
| batch_size: 128 | |
| shuffle: false | |
| } | |
| } | |
| layer { | |
| name: "cifar" | |
| type: "HDF5Data" | |
| top: "data" | |
| top: "label" | |
| include { | |
| phase: TEST | |
| } | |
| hdf5_data_param { | |
| source: "../cifar-test.txt" | |
| batch_size: 100 | |
| } | |
| } | |
| layer { | |
| name: "conv1" | |
| type: "Convolution" | |
| bottom: "data" | |
| top: "conv1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| pad: 2 | |
| kernel_size: 5 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu1" | |
| type: "ReLU" | |
| bottom: "conv1" | |
| top: "conv1" | |
| } | |
| layer { | |
| name: "cccp1" | |
| type: "Convolution" | |
| bottom: "conv1" | |
| top: "cccp1" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 160 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp1" | |
| type: "ReLU" | |
| bottom: "cccp1" | |
| top: "cccp1" | |
| } | |
| layer { | |
| name: "cccp2" | |
| type: "Convolution" | |
| bottom: "cccp1" | |
| top: "cccp2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 96 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp2" | |
| type: "ReLU" | |
| bottom: "cccp2" | |
| top: "cccp2" | |
| } | |
| layer { | |
| name: "pool1" | |
| type: "Pooling" | |
| bottom: "cccp2" | |
| top: "pool1" | |
| pooling_param { | |
| pool: MAX | |
| kernel_size: 3 | |
| stride: 2 | |
| engine: CAFFE | |
| } | |
| } | |
| layer { | |
| name: "drop3" | |
| type: "Dropout" | |
| bottom: "pool1" | |
| top: "pool1" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "conv2" | |
| type: "Convolution" | |
| bottom: "pool1" | |
| top: "conv2" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| pad: 2 | |
| kernel_size: 5 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu2" | |
| type: "ReLU" | |
| bottom: "conv2" | |
| top: "conv2" | |
| } | |
| layer { | |
| name: "cccp3" | |
| type: "Convolution" | |
| bottom: "conv2" | |
| top: "cccp3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp3" | |
| type: "ReLU" | |
| bottom: "cccp3" | |
| top: "cccp3" | |
| } | |
| layer { | |
| name: "cccp4" | |
| type: "Convolution" | |
| bottom: "cccp3" | |
| top: "cccp4" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp4" | |
| type: "ReLU" | |
| bottom: "cccp4" | |
| top: "cccp4" | |
| } | |
| layer { | |
| name: "pool2" | |
| type: "Pooling" | |
| bottom: "cccp4" | |
| top: "pool2" | |
| pooling_param { | |
| pool: AVE | |
| kernel_size: 3 | |
| stride: 2 | |
| } | |
| } | |
| layer { | |
| name: "drop6" | |
| type: "Dropout" | |
| bottom: "pool2" | |
| top: "pool2" | |
| dropout_param { | |
| dropout_ratio: 0.5 | |
| } | |
| } | |
| layer { | |
| name: "conv3" | |
| type: "Convolution" | |
| bottom: "pool2" | |
| top: "conv3" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| pad: 1 | |
| kernel_size: 3 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu3" | |
| type: "ReLU" | |
| bottom: "conv3" | |
| top: "conv3" | |
| } | |
| layer { | |
| name: "cccp5" | |
| type: "Convolution" | |
| bottom: "conv3" | |
| top: "cccp5" | |
| param { | |
| lr_mult: 1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 2 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 192 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp5" | |
| type: "ReLU" | |
| bottom: "cccp5" | |
| top: "cccp5" | |
| } | |
| layer { | |
| name: "cccp6" | |
| type: "Convolution" | |
| bottom: "cccp5" | |
| top: "cccp6" | |
| param { | |
| lr_mult: 0.1 | |
| decay_mult: 1 | |
| } | |
| param { | |
| lr_mult: 0.1 | |
| decay_mult: 0 | |
| } | |
| convolution_param { | |
| num_output: 10 | |
| kernel_size: 1 | |
| group: 1 | |
| weight_filler { | |
| type: "gaussian" | |
| std: 0.05 | |
| } | |
| bias_filler { | |
| type: "constant" | |
| value: 0 | |
| } | |
| } | |
| } | |
| layer { | |
| name: "relu_cccp6" | |
| type: "ReLU" | |
| bottom: "cccp6" | |
| top: "cccp6" | |
| } | |
| layer { | |
| name: "pool3" | |
| type: "Pooling" | |
| bottom: "cccp6" | |
| top: "pool3" | |
| pooling_param { | |
| pool: AVE | |
| kernel_size: 8 | |
| stride: 1 | |
| } | |
| } | |
| layer { | |
| name: "accuracy" | |
| type: "Accuracy" | |
| bottom: "pool3" | |
| bottom: "label" | |
| top: "accuracy" | |
| include { | |
| phase: TEST | |
| } | |
| } | |
| layer { | |
| name: "loss" | |
| type: "SoftmaxWithLoss" | |
| bottom: "pool3" | |
| bottom: "label" | |
| top: "loss" | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Why does layer
pool2use average pooling?layer { name: "pool2" type: "Pooling" bottom: "cccp4" top: "pool2" pooling_param { pool: AVE # shouldn't this be MAX? kernel_size: 3 stride: 2 } }