# Faster-RCNN network. Based on https://github.com/rbgirshick/py-faster-rcnn/blob/master/models/pascal_voc/ZF/faster_rcnn_alt_opt/faster_rcnn_test.pt
name: "ZF"

input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}

input: "im_info"
input_shape {
  dim: 1
  dim: 3
}

#========= conv1-conv5 ============

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    kernel_size: 7
    pad: 3
    stride: 2
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "conv1"
  top: "norm1"
  lrn_param {
    local_size: 3
    alpha: 0.00005
    beta: 0.75
    norm_region: WITHIN_CHANNEL
    engine: CAFFE
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "norm1"
  top: "pool1"
  pooling_param {
    kernel_size: 3
    stride: 2
    pad: 1
    pool: MAX
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  convolution_param {
    num_output: 256
    kernel_size: 5
    pad: 2
    stride: 2
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "conv2"
  top: "norm2"
  lrn_param {
    local_size: 3
    alpha: 0.00005
    beta: 0.75
    norm_region: WITHIN_CHANNEL
    engine: CAFFE
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "norm2"
  top: "pool2"
  pooling_param {
    kernel_size: 3
    stride: 2
    pad: 1
    pool: MAX
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  convolution_param {
    num_output: 384
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 384
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 256
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}

#========= RPN ============


layer {
  name: "rpn_conv1"
  type: "Convolution"
  bottom: "conv5"
  top: "rpn_conv1"
  convolution_param {
    num_output: 256
    kernel_size: 3 pad: 1 stride: 1
  }
}
layer {
  name: "rpn_relu1"
  type: "ReLU"
  bottom: "rpn_conv1"
  top: "rpn_conv1"
}
layer {
  name: "rpn_cls_score"
  type: "Convolution"
  bottom: "rpn_conv1"
  top: "rpn_cls_score"
  convolution_param {
    num_output: 18   # 2(bg/fg) * 9(anchors)
    kernel_size: 1 pad: 0 stride: 1
  }
}
layer {
  name: "rpn_bbox_pred"
  type: "Convolution"
  bottom: "rpn_conv1"
  top: "rpn_bbox_pred"
  convolution_param {
    num_output: 36   # 4 * 9(anchors)
    kernel_size: 1 pad: 0 stride: 1
  }
}
layer {
   bottom: "rpn_cls_score"
   top: "rpn_cls_score_reshape"
   name: "rpn_cls_score_reshape"
   type: "Reshape"
   reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }
}

#========= RoI Proposal ============

layer {
  name: "rpn_cls_prob"
  type: "Softmax"
  bottom: "rpn_cls_score_reshape"
  top: "rpn_cls_prob"
}
layer {
  name: 'rpn_cls_prob_reshape'
  type: 'Reshape'
  bottom: 'rpn_cls_prob'
  top: 'rpn_cls_prob_reshape'
  reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }
}
# layer {
#   name: 'proposal'
#   type: 'Python'
#   bottom: 'rpn_cls_prob_reshape'
#   bottom: 'rpn_bbox_pred'
#   bottom: 'im_info'
#   top: 'rois'
#   python_param {
#     module: 'rpn.proposal_layer'
#     layer: 'ProposalLayer'
#     param_str: "'feat_stride': 16"
#   }
# }
layer {
  name: 'proposal'
  type: 'Proposal'
  bottom: 'rpn_cls_prob_reshape'
  bottom: 'rpn_bbox_pred'
  bottom: 'im_info'
  top: 'rois'
  proposal_param {
    ratio: 0.5
    ratio: 1.0
    ratio: 2.0
    scale: 8
    scale: 16
    scale: 32
  }
}

#========= RCNN ============

layer {
  name: "roi_pool_conv5"
  type: "ROIPooling"
  bottom: "conv5"
  bottom: "rois"
  top: "roi_pool_conv5"
  roi_pooling_param {
    pooled_w: 6
    pooled_h: 6
    spatial_scale: 0.0625 # 1/16
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "roi_pool_conv5"
  top: "fc6"
  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
    scale_train: false
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  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
    scale_train: false
  }
}
layer {
  name: "cls_score"
  type: "InnerProduct"
  bottom: "fc7"
  top: "cls_score"
  inner_product_param {
    num_output: 21
  }
}
layer {
  name: "bbox_pred"
  type: "InnerProduct"
  bottom: "fc7"
  top: "bbox_pred"
  inner_product_param {
    num_output: 84
  }
}
layer {
  name: "cls_prob"
  type: "Softmax"
  bottom: "cls_score"
  top: "cls_prob"
  loss_param {
    ignore_label: -1
    normalize: true
  }
}

# ======== Postprocessing ==========
# cls_prob has a shape [numPriors x 21]. Flatten it to [1 x numPriors*21].
layer {
  name: "cls_prob_reshape"
  type: "Reshape"
  bottom: "cls_prob"
  top: "cls_prob_reshape"
  reshape_param {
    shape {
      dim: 1
      dim: -1
    }
  }
}
# Reshape bounding boxes from [numPriors x 84] to [1 x numPriors*84].
layer {
  name: "bbox_pred_reshape"
  type: "Reshape"
  bottom: "bbox_pred"
  top: "bbox_pred_reshape"
  reshape_param {
    shape {
      dim: 1
      dim: -1
    }
  }
}
# Proposal layer generates [numPriors x 5] blob where 0th column are batch indices
# and only the rest are bounding boxes.
layer {
    name: "proposal_crop"
    type: "Slice"
    bottom: "rois"
    top: "proposal_batch_ids"
    top: "proposal_bboxes"
    slice_param {
      axis: 1
      slice_point: 1
    }
}
# Reshape it to [1 x 1 x numPriors*4]
layer {
    name: "proposal_reshape"
    type: "Reshape"
    bottom: "proposal_bboxes"
    top: "proposal_reshape"
    reshape_param {
        shape {
            dim: 1
            dim: 1
            dim: -1
        }
    }
}
layer {
  name: "detection_out"
  type: "DetectionOutput"
  bottom: "bbox_pred_reshape"
  bottom: "cls_prob_reshape"
  bottom: "proposal_reshape"
  top: "detection_out"
  detection_output_param {
    num_classes: 21
    share_location: false
    background_label_id: 0
    nms_param {
      nms_threshold: 0.3
    }
    code_type: CENTER_SIZE
    keep_top_k: 100
    variance_encoded_in_target: true
    normalized_bbox: false
  }
}