experiments for no bbox reg (train|test) and piecewise training

experiments/no_bbox_reg.yml

@@ -0,0 +1,5 @@
+EXP_DIR: "no_bbox_reg"
+TRAIN:
+  BBOX_REG: False
+TEST:
+  BBOX_REG: False

experiments/piecewise.yml

@@ -0,0 +1 @@
+EXP_DIR: "piecewise"

models/CaffeNet/no_bbox_reg/solver.prototxt

@@ -0,0 +1,15 @@
+train_net: "models/CaffeNet/no_bbox_reg/train.prototxt"
+base_lr: 0.001
+lr_policy: "step"
+gamma: 0.1
+stepsize: 30000
+display: 20
+average_loss: 100
+momentum: 0.9
+weight_decay: 0.0005
+# We disable standard caffe solver snapshotting and implement our own snapshot
+# function
+snapshot: 0
+# We still use the snapshot prefix, though
+snapshot_prefix: "caffenet_fast_rcnn"
+#debug_info: true

models/CaffeNet/no_bbox_reg/test.prototxt

@@ -0,0 +1,292 @@
+name: "CaffeNet"
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 227
+  dim: 227
+}
+input: "rois"
+input_shape {
+  dim: 1 # to be changed on-the-fly to num ROIs
+  dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing
+}
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "data"
+  top: "conv1"
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  param {
+    lr_mult: 0
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 96
+    kernel_size: 11
+    stride: 4
+  }
+}
+layer {
+  name: "relu1"
+  type: "ReLU"
+  bottom: "conv1"
+  top: "conv1"
+}
+layer {
+  name: "pool1"
+  type: "Pooling"
+  bottom: "conv1"
+  top: "pool1"
+  pooling_param {
+    pool: MAX
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "norm1"
+  type: "LRN"
+  bottom: "pool1"
+  top: "norm1"
+  lrn_param {
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+}
+layer {
+  name: "conv2"
+  type: "Convolution"
+  bottom: "norm1"
+  top: "conv2"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 2
+    kernel_size: 5
+    group: 2
+  }
+}
+layer {
+  name: "relu2"
+  type: "ReLU"
+  bottom: "conv2"
+  top: "conv2"
+}
+layer {
+  name: "pool2"
+  type: "Pooling"
+  bottom: "conv2"
+  top: "pool2"
+  pooling_param {
+    pool: MAX
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "norm2"
+  type: "LRN"
+  bottom: "pool2"
+  top: "norm2"
+  lrn_param {
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+}
+layer {
+  name: "conv3"
+  type: "Convolution"
+  bottom: "norm2"
+  top: "conv3"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 384
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu3"
+  type: "ReLU"
+  bottom: "conv3"
+  top: "conv3"
+}
+layer {
+  name: "conv4"
+  type: "Convolution"
+  bottom: "conv3"
+  top: "conv4"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 384
+    pad: 1
+    kernel_size: 3
+    group: 2
+  }
+}
+layer {
+  name: "relu4"
+  type: "ReLU"
+  bottom: "conv4"
+  top: "conv4"
+}
+layer {
+  name: "conv5"
+  type: "Convolution"
+  bottom: "conv4"
+  top: "conv5"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    group: 2
+  }
+}
+layer {
+  name: "relu5"
+  type: "ReLU"
+  bottom: "conv5"
+  top: "conv5"
+}
+layer {
+  name: "roi_pool5"
+  type: "ROIPooling"
+  bottom: "conv5"
+  bottom: "rois"
+  top: "pool5"
+  roi_pooling_param {
+    pooled_w: 6
+    pooled_h: 6
+    spatial_scale: 0.0625 # 1/16
+  }
+}
+layer {
+  name: "fc6"
+  type: "InnerProduct"
+  bottom: "pool5"
+  top: "fc6"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layer {
+  name: "relu6"
+  type: "ReLU"
+  bottom: "fc6"
+  top: "fc6"
+}
+layer {
+  name: "drop6"
+  type: "Dropout"
+  bottom: "fc6"
+  top: "fc6"
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layer {
+  name: "fc7"
+  type: "InnerProduct"
+  bottom: "fc6"
+  top: "fc7"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layer {
+  name: "relu7"
+  type: "ReLU"
+  bottom: "fc7"
+  top: "fc7"
+}
+layer {
+  name: "drop7"
+  type: "Dropout"
+  bottom: "fc7"
+  top: "fc7"
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layer {
+  name: "cls_score"
+  type: "InnerProduct"
+  bottom: "fc7"
+  top: "cls_score"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  inner_product_param {
+    num_output: 21
+    weight_filler {
+      type: "gaussian"
+      std: 0.01
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "cls_prob"
+  type: "Softmax"
+  bottom: "cls_score"
+  top: "cls_prob"
+}