define pascal finetuning models

diff --git a/models/pascal_finetune.prototxt b/models/pascal_finetune.prototxt
new file mode 100644 (file)
index 0000000..7b2b05d
--- /dev/null
+++ b/models/pascal_finetune.prototxt
@@ -0,0 +1,368 @@
+name: "CaffeNet"
+layers {
+  layer {
+    name: "data"
+    type: "window_data"
+    source: "/work5/rbg/convnet-selective-search/selective-search-data/window_file_2007_train.txt"
+    meanfile: "/home/rbg/working/caffe-rbg/data/ilsvrc2012_mean.binaryproto"
+    batchsize: 128
+    cropsize: 227
+    mirror: true
+    det_fg_threshold: 0.6
+    det_bg_threshold: 0.3
+    det_fg_fraction: 0.25
+  }
+  top: "data"
+  top: "label"
+}
+layers {
+  layer {
+    name: "conv1"
+    type: "conv"
+    num_output: 96
+    kernelsize: 11
+    stride: 4
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "data"
+  top: "conv1"
+}
+layers {
+  layer {
+    name: "relu1"
+    type: "relu"
+  }
+  bottom: "conv1"
+  top: "conv1"
+}
+layers {
+  layer {
+    name: "pool1"
+    type: "pool"
+    pool: MAX
+    kernelsize: 3
+    stride: 2
+  }
+  bottom: "conv1"
+  top: "pool1"
+}
+layers {
+  layer {
+    name: "norm1"
+    type: "lrn"
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+  bottom: "pool1"
+  top: "norm1"
+}
+layers {
+  layer {
+    name: "pad2"
+    type: "padding"
+    pad: 2
+  }
+  bottom: "norm1"
+  top: "pad2"
+}
+layers {
+  layer {
+    name: "conv2"
+    type: "conv"
+    num_output: 256
+    group: 2
+    kernelsize: 5
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad2"
+  top: "conv2"
+}
+layers {
+  layer {
+    name: "relu2"
+    type: "relu"
+  }
+  bottom: "conv2"
+  top: "conv2"
+}
+layers {
+  layer {
+    name: "pool2"
+    type: "pool"
+    pool: MAX
+    kernelsize: 3
+    stride: 2
+  }
+  bottom: "conv2"
+  top: "pool2"
+}
+layers {
+  layer {
+    name: "norm2"
+    type: "lrn"
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+  bottom: "pool2"
+  top: "norm2"
+}
+layers {
+  layer {
+    name: "pad3"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "norm2"
+  top: "pad3"
+}
+layers {
+  layer {
+    name: "conv3"
+    type: "conv"
+    num_output: 384
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad3"
+  top: "conv3"
+}
+layers {
+  layer {
+    name: "relu3"
+    type: "relu"
+  }
+  bottom: "conv3"
+  top: "conv3"
+}
+layers {
+  layer {
+    name: "pad4"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "conv3"
+  top: "pad4"
+}
+layers {
+  layer {
+    name: "conv4"
+    type: "conv"
+    num_output: 384
+    group: 2
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad4"
+  top: "conv4"
+}
+layers {
+  layer {
+    name: "relu4"
+    type: "relu"
+  }
+  bottom: "conv4"
+  top: "conv4"
+}
+layers {
+  layer {
+    name: "pad5"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "conv4"
+  top: "pad5"
+}
+layers {
+  layer {
+    name: "conv5"
+    type: "conv"
+    num_output: 256
+    group: 2
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad5"
+  top: "conv5"
+}
+layers {
+  layer {
+    name: "relu5"
+    type: "relu"
+  }
+  bottom: "conv5"
+  top: "conv5"
+}
+layers {
+  layer {
+    name: "pool5"
+    type: "pool"
+    kernelsize: 3
+    pool: MAX
+    stride: 2
+  }
+  bottom: "conv5"
+  top: "pool5"
+}
+layers {
+  layer {
+    name: "fc6"
+    type: "innerproduct"
+    num_output: 4096
+    weight_filler {
+      type: "gaussian"
+      std: 0.005
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pool5"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "relu6"
+    type: "relu"
+  }
+  bottom: "fc6"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "drop6"
+    type: "dropout"
+    dropout_ratio: 0.5
+  }
+  bottom: "fc6"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "fc7"
+    type: "innerproduct"
+    num_output: 4096
+    weight_filler {
+      type: "gaussian"
+      std: 0.005
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "fc6"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "relu7"
+    type: "relu"
+  }
+  bottom: "fc7"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "drop7"
+    type: "dropout"
+    dropout_ratio: 0.5
+  }
+  bottom: "fc7"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "fc8"
+    type: "innerproduct"
+    num_output: 21
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+    can_clobber: false
+  }
+  bottom: "fc7"
+  top: "fc8"
+}
+layers {
+  layer {
+    name: "loss"
+    type: "softmax_loss"
+  }
+  bottom: "fc8"
+  bottom: "label"
+}

diff --git a/models/pascal_finetune_solver.prototxt b/models/pascal_finetune_solver.prototxt
new file mode 100644 (file)
index 0000000..eaed2b3
--- /dev/null
+++ b/models/pascal_finetune_solver.prototxt
@@ -0,0 +1,14 @@
+train_net: "examples/pascal_finetune.prototxt"
+test_net: "examples/pascal_finetune_val.prototxt"
+test_iter: 100
+test_interval: 400
+base_lr: 0.0001
+lr_policy: "step"
+gamma: 0.1
+stepsize: 50000
+display: 20
+max_iter: 400000
+momentum: 0.9
+weight_decay: 0.0005
+snapshot: 10000
+snapshot_prefix: "./snapshots/pascal_finetune_train"

diff --git a/models/pascal_finetune_val.prototxt b/models/pascal_finetune_val.prototxt
new file mode 100644 (file)
index 0000000..fe1a269
--- /dev/null
+++ b/models/pascal_finetune_val.prototxt
@@ -0,0 +1,376 @@
+name: "CaffeNet"
+layers {
+  layer {
+    name: "data"
+    type: "window_data"
+    source: "/work5/rbg/convnet-selective-search/selective-search-data/window_file_2007_val.txt"
+    meanfile: "/home/rbg/working/caffe-rbg/data/ilsvrc2012_mean.binaryproto"
+    batchsize: 128
+    cropsize: 227
+    mirror: true
+    det_fg_threshold: 0.6
+    det_bg_threshold: 0.3
+    det_fg_fraction: 0.5
+  }
+  top: "data"
+  top: "label"
+}
+layers {
+  layer {
+    name: "conv1"
+    type: "conv"
+    num_output: 96
+    kernelsize: 11
+    stride: 4
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "data"
+  top: "conv1"
+}
+layers {
+  layer {
+    name: "relu1"
+    type: "relu"
+  }
+  bottom: "conv1"
+  top: "conv1"
+}
+layers {
+  layer {
+    name: "pool1"
+    type: "pool"
+    pool: MAX
+    kernelsize: 3
+    stride: 2
+  }
+  bottom: "conv1"
+  top: "pool1"
+}
+layers {
+  layer {
+    name: "norm1"
+    type: "lrn"
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+  bottom: "pool1"
+  top: "norm1"
+}
+layers {
+  layer {
+    name: "pad2"
+    type: "padding"
+    pad: 2
+  }
+  bottom: "norm1"
+  top: "pad2"
+}
+layers {
+  layer {
+    name: "conv2"
+    type: "conv"
+    num_output: 256
+    group: 2
+    kernelsize: 5
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad2"
+  top: "conv2"
+}
+layers {
+  layer {
+    name: "relu2"
+    type: "relu"
+  }
+  bottom: "conv2"
+  top: "conv2"
+}
+layers {
+  layer {
+    name: "pool2"
+    type: "pool"
+    pool: MAX
+    kernelsize: 3
+    stride: 2
+  }
+  bottom: "conv2"
+  top: "pool2"
+}
+layers {
+  layer {
+    name: "norm2"
+    type: "lrn"
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+  bottom: "pool2"
+  top: "norm2"
+}
+layers {
+  layer {
+    name: "pad3"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "norm2"
+  top: "pad3"
+}
+layers {
+  layer {
+    name: "conv3"
+    type: "conv"
+    num_output: 384
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad3"
+  top: "conv3"
+}
+layers {
+  layer {
+    name: "relu3"
+    type: "relu"
+  }
+  bottom: "conv3"
+  top: "conv3"
+}
+layers {
+  layer {
+    name: "pad4"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "conv3"
+  top: "pad4"
+}
+layers {
+  layer {
+    name: "conv4"
+    type: "conv"
+    num_output: 384
+    group: 2
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad4"
+  top: "conv4"
+}
+layers {
+  layer {
+    name: "relu4"
+    type: "relu"
+  }
+  bottom: "conv4"
+  top: "conv4"
+}
+layers {
+  layer {
+    name: "pad5"
+    type: "padding"
+    pad: 1
+  }
+  bottom: "conv4"
+  top: "pad5"
+}
+layers {
+  layer {
+    name: "conv5"
+    type: "conv"
+    num_output: 256
+    group: 2
+    kernelsize: 3
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pad5"
+  top: "conv5"
+}
+layers {
+  layer {
+    name: "relu5"
+    type: "relu"
+  }
+  bottom: "conv5"
+  top: "conv5"
+}
+layers {
+  layer {
+    name: "pool5"
+    type: "pool"
+    kernelsize: 3
+    pool: MAX
+    stride: 2
+  }
+  bottom: "conv5"
+  top: "pool5"
+}
+layers {
+  layer {
+    name: "fc6"
+    type: "innerproduct"
+    num_output: 4096
+    weight_filler {
+      type: "gaussian"
+      std: 0.005
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "pool5"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "relu6"
+    type: "relu"
+  }
+  bottom: "fc6"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "drop6"
+    type: "dropout"
+    dropout_ratio: 0.5
+  }
+  bottom: "fc6"
+  top: "fc6"
+}
+layers {
+  layer {
+    name: "fc7"
+    type: "innerproduct"
+    num_output: 4096
+    weight_filler {
+      type: "gaussian"
+      std: 0.005
+    }
+    bias_filler {
+      type: "constant"
+      value: 1.
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "fc6"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "relu7"
+    type: "relu"
+  }
+  bottom: "fc7"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "drop7"
+    type: "dropout"
+    dropout_ratio: 0.5
+  }
+  bottom: "fc7"
+  top: "fc7"
+}
+layers {
+  layer {
+    name: "fc8"
+    type: "innerproduct"
+    num_output: 21
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+    blobs_lr: 1.
+    blobs_lr: 2.
+    weight_decay: 1.
+    weight_decay: 0.
+  }
+  bottom: "fc7"
+  top: "fc8"
+}
+layers {
+  layer {
+    name: "prob"
+    type: "softmax"
+  }
+  bottom: "fc8"
+  top: "prob"
+}
+layers {
+  layer {
+    name: "accuracy"
+    type: "accuracy"
+  }
+  bottom: "prob"
+  bottom: "label"
+  top: "accuracy"
+}