keras Mask Rcnn代码走读（五）- Proposal classifier and BBox regressor

作用为对proposal 区域进行分类及位置大小回归，经过ROI之后，proposal 变成固定大小的feature，用卷积核为特征图尺寸的卷积代替平坦化层，最后用全连接层完成分类及bbox回归。TimeDistributed为实现一张大图多个proposal同时并行计算。

# Network Heads    
 # Proposal classifier and BBox regressor heads    
 # output shapes:   
  #     mrcnn_class_logits: [batch, num_rois, NUM_CLASSES] classifier logits (before softmax)   
   #     mrcnn_class: [batch, num_rois, NUM_CLASSES] classifier probabilities   
    #     mrcnn_bbox(deltas): [batch, num_rois, NUM_CLASSES, (dy, dx, log(dh), log(dw))]

############################################################
#  Feature Pyramid Network Heads
############################################################

def fpn_classifier_graph(rois, feature_maps, image_meta,
                         pool_size, num_classes, train_bn=True,
                         fc_layers_size=1024):
    """Builds the computation graph of the feature pyramid network classifier
    and regressor heads.

    rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized
          coordinates.
    feature_maps: List of feature maps from different layers of the pyramid,
                  [P2, P3, P4, P5]. Each has a different resolution.
    image_meta: [batch, (meta data)] Image details. See compose_image_meta()
    pool_size: The width of the square feature map generated from ROI Pooling.
    num_classes: number of classes, which determines the depth of the results
    train_bn: Boolean. Train or freeze Batch Norm layers
    fc_layers_size: Size of the 2 FC layers

    Returns:
        logits: [batch, num_rois, NUM_CLASSES] classifier logit