removing VGG_CNN_S

models/VGG_CNN_S/deploy.prototxt

-name: "VGG_CNN_S"
-input: "data"
-input_dim: 1
-input_dim: 3
-input_dim: 224
-input_dim: 224
-input: "rois"
-input_dim: 1 # to be changed on-the-fly to num ROIs
-input_dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing
-input_dim: 1
-input_dim: 1
-layers {
-  bottom: "data"
-  top: "conv1"
-  name: "conv1"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 96
-    kernel_size: 7
-    stride: 2
-  }
-  # Learning parameters
-  blobs_lr: 0
-  blobs_lr: 0
-  weight_decay: 0
-  weight_decay: 0
-}
-layers {
-  bottom: "conv1"
-  top: "conv1"
-  name: "relu1"
-  type: RELU
-}
-layers {
-  bottom: "conv1"
-  top: "norm1"
-  name: "norm1"
-  type: LRN
-  lrn_param {
-    local_size: 5
-    alpha: 0.0005
-    beta: 0.75
-    k: 2
-  }
-}
-layers {
-  bottom: "norm1"
-  top: "pool1"
-  name: "pool1"
-  type: POOLING
-  pooling_param {
-    pool: MAX
-    kernel_size: 3
-    stride: 3
-  }
-}
-layers {
-  bottom: "pool1"
-  top: "conv2"
-  name: "conv2"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 256
-    kernel_size: 5
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv2"
-  top: "conv2"
-  name: "relu2"
-  type: RELU
-}
-layers {
-  bottom: "conv2"
-  top: "pool2"
-  name: "pool2"
-  type: POOLING
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-  }
-}
-layers {
-  bottom: "pool2"
-  top: "conv3"
-  name: "conv3"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv3"
-  top: "conv3"
-  name: "relu3"
-  type: RELU
-}
-layers {
-  bottom: "conv3"
-  top: "conv4"
-  name: "conv4"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv4"
-  top: "conv4"
-  name: "relu4"
-  type: RELU
-}
-layers {
-  bottom: "conv4"
-  top: "conv5"
-  name: "conv5"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv5"
-  top: "conv5"
-  name: "relu5"
-  type: RELU
-}
-layers {
-  name: "roi_pool5"
-  type: ROI_POOLING
-  bottom: "conv5"
-  bottom: "rois"
-  top: "pool5"
-  roi_pooling_param {
-    pooled_w: 6
-    pooled_h: 6
-  }
-}
-layers {
-  bottom: "pool5"
-  top: "fc6"
-  name: "fc6"
-  type: INNER_PRODUCT
-  inner_product_param {
-    num_output: 4096
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "fc6"
-  top: "fc6"
-  name: "relu6"
-  type: RELU
-}
-layers {
-  bottom: "fc6"
-  top: "fc6"
-  name: "drop6"
-  type: DROPOUT
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layers {
-  bottom: "fc6"
-  top: "fc7"
-  name: "fc7"
-  type: INNER_PRODUCT
-  inner_product_param {
-    num_output: 4096
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "fc7"
-  top: "fc7"
-  name: "relu7"
-  type: RELU
-}
-layers {
-  bottom: "fc7"
-  top: "fc7"
-  name: "drop7"
-  type: DROPOUT
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layers {
-  name: "fc8_pascal"
-  type: INNER_PRODUCT
-  bottom: "fc7"
-  top: "fc8_pascal"
-  inner_product_param {
-    num_output: 21
-    weight_filler {
-      type: "gaussian"
-      std: 0.01
-    }
-    bias_filler {
-      type: "constant"
-      value: 0
-    }
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  name: "fc8_pascal_bbox"
-  type: INNER_PRODUCT
-  bottom: "fc7"
-  top: "fc8_pascal_bbox"
-  inner_product_param {
-    num_output: 84
-    weight_filler {
-      type: "gaussian"
-      std: 0.001
-    }
-    bias_filler {
-      type: "constant"
-      value: 0
-    }
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  name: "prob"
-  type: SOFTMAX
-  bottom: "fc8_pascal"
-  top: "prob"
-}

models/VGG_CNN_S/solver.prototxt

-train_net: "models/VGG_CNN_S/train.prototxt"
-base_lr: 0.001
-lr_policy: "step"
-gamma: 0.1
-stepsize: 30000
-display: 20
-average_loss: 100
-max_iter: 500000
-iter_size: 1
-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: "snapshots/vgg_cnn_s_fast_rcnn"
-#debug_info: true

models/VGG_CNN_S/train.prototxt

-name: "VGG_CNN_S"
-input: "data"
-input_dim: 1
-input_dim: 3
-input_dim: 224
-input_dim: 224
-input: "rois"
-input_dim: 1 # to be changed on-the-fly to num ROIs
-input_dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing
-input_dim: 1
-input_dim: 1
-input: "labels"
-input_dim: 1 # to be changed on-the-fly to match num ROIs
-input_dim: 1
-input_dim: 1
-input_dim: 1
-input: "bbox_targets"
-input_dim: 1  # to be changed on-the-fly to match num ROIs
-input_dim: 84 # 4 * K (=21) classes
-input_dim: 1
-input_dim: 1
-input: "bbox_loss_weights"
-input_dim: 1  # to be changed on-the-fly to match num ROIs
-input_dim: 84 # 4 * K (=21) classes
-input_dim: 1
-input_dim: 1
-layers {
-  bottom: "data"
-  top: "conv1"
-  name: "conv1"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 96
-    kernel_size: 7
-    stride: 2
-  }
-  # Learning parameters
-  blobs_lr: 0
-  blobs_lr: 0
-  weight_decay: 0
-  weight_decay: 0
-}
-layers {
-  bottom: "conv1"
-  top: "conv1"
-  name: "relu1"
-  type: RELU
-}
-layers {
-  bottom: "conv1"
-  top: "norm1"
-  name: "norm1"
-  type: LRN
-  lrn_param {
-    local_size: 5
-    alpha: 0.0005
-    beta: 0.75
-    k: 2
-  }
-}
-layers {
-  bottom: "norm1"
-  top: "pool1"
-  name: "pool1"
-  type: POOLING
-  pooling_param {
-    pool: MAX
-    kernel_size: 3
-    stride: 3
-  }
-}
-layers {
-  bottom: "pool1"
-  top: "conv2"
-  name: "conv2"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 256
-    kernel_size: 5
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv2"
-  top: "conv2"
-  name: "relu2"
-  type: RELU
-}
-layers {
-  bottom: "conv2"
-  top: "pool2"
-  name: "pool2"
-  type: POOLING
-  pooling_param {
-    pool: MAX
-    kernel_size: 2
-    stride: 2
-  }
-}
-layers {
-  bottom: "pool2"
-  top: "conv3"
-  name: "conv3"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv3"
-  top: "conv3"
-  name: "relu3"
-  type: RELU
-}
-layers {
-  bottom: "conv3"
-  top: "conv4"
-  name: "conv4"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv4"
-  top: "conv4"
-  name: "relu4"
-  type: RELU
-}
-layers {
-  bottom: "conv4"
-  top: "conv5"
-  name: "conv5"
-  type: CONVOLUTION
-  convolution_param {
-    num_output: 512
-    pad: 1
-    kernel_size: 3
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "conv5"
-  top: "conv5"
-  name: "relu5"
-  type: RELU
-}
-layers {
-  name: "roi_pool5"
-  type: ROI_POOLING
-  bottom: "conv5"
-  bottom: "rois"
-  top: "pool5"
-  roi_pooling_param {
-    pooled_w: 6
-    pooled_h: 6
-  }
-}
-layers {
-  bottom: "pool5"
-  top: "fc6"
-  name: "fc6"
-  type: INNER_PRODUCT
-  inner_product_param {
-    num_output: 4096
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "fc6"
-  top: "fc6"
-  name: "relu6"
-  type: RELU
-}
-layers {
-  bottom: "fc6"
-  top: "fc6"
-  name: "drop6"
-  type: DROPOUT
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layers {
-  bottom: "fc6"
-  top: "fc7"
-  name: "fc7"
-  type: INNER_PRODUCT
-  inner_product_param {
-    num_output: 4096
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  bottom: "fc7"
-  top: "fc7"
-  name: "relu7"
-  type: RELU
-}
-layers {
-  bottom: "fc7"
-  top: "fc7"
-  name: "drop7"
-  type: DROPOUT
-  dropout_param {
-    dropout_ratio: 0.5
-  }
-}
-layers {
-  name: "fc8_pascal"
-  type: INNER_PRODUCT
-  bottom: "fc7"
-  top: "fc8_pascal"
-  inner_product_param {
-    num_output: 21
-    weight_filler {
-      type: "gaussian"
-      std: 0.01
-    }
-    bias_filler {
-      type: "constant"
-      value: 0
-    }
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  name: "fc8_pascal_bbox"
-  type: INNER_PRODUCT
-  bottom: "fc7"
-  top: "fc8_pascal_bbox"
-  inner_product_param {
-    num_output: 84
-    weight_filler {
-      type: "gaussian"
-      std: 0.001
-    }
-    bias_filler {
-      type: "constant"
-      value: 0
-    }
-  }
-  # Learning parameters
-  blobs_lr: 1
-  blobs_lr: 2
-  weight_decay: 1
-  weight_decay: 0
-}
-layers {
-  name: "loss"
-  type: SOFTMAX_LOSS
-  bottom: "fc8_pascal"
-  bottom: "labels"
-  top: "loss"
-}
-layers {
-  name: "loss_bbox"
-  type: SMOOTH_L1_LOSS
-  bottom: "fc8_pascal_bbox"
-  bottom: "bbox_targets"
-  bottom: "bbox_loss_weights"
-  top: "loss_bbox"
-  loss_weight: 1
-}