example/rcnn/rcnn/symbol/symbol_resnet.py [76:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    rpn_relu = mx.symbol.Activation(data=rpn_conv, act_type="relu", name="rpn_relu")
    rpn_cls_score = mx.symbol.Convolution(
        data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=2 * num_anchors, name="rpn_cls_score")
    rpn_bbox_pred = mx.symbol.Convolution(
        data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=4 * num_anchors, name="rpn_bbox_pred")

    # prepare rpn data
    rpn_cls_score_reshape = mx.symbol.Reshape(
        data=rpn_cls_score, shape=(0, 2, -1, 0), name="rpn_cls_score_reshape")

    # classification
    rpn_cls_prob = mx.symbol.SoftmaxOutput(data=rpn_cls_score_reshape, label=rpn_label, multi_output=True,
                                           normalization='valid', use_ignore=True, ignore_label=-1, name="rpn_cls_prob")
    # bounding box regression
    rpn_bbox_loss_ = rpn_bbox_weight * mx.symbol.smooth_l1(name='rpn_bbox_loss_', scalar=3.0, data=(rpn_bbox_pred - rpn_bbox_target))
    rpn_bbox_loss = mx.sym.MakeLoss(name='rpn_bbox_loss', data=rpn_bbox_loss_, grad_scale=1.0 / config.TRAIN.RPN_BATCH_SIZE)

    # ROI proposal
    rpn_cls_act = mx.symbol.SoftmaxActivation(
        data=rpn_cls_score_reshape, mode="channel", name="rpn_cls_act")
    rpn_cls_act_reshape = mx.symbol.Reshape(
        data=rpn_cls_act, shape=(0, 2 * num_anchors, -1, 0), name='rpn_cls_act_reshape')
    if config.TRAIN.CXX_PROPOSAL:
        rois = mx.contrib.symbol.Proposal(
            cls_prob=rpn_cls_act_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois',
            feature_stride=config.RPN_FEAT_STRIDE, scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
            rpn_pre_nms_top_n=config.TRAIN.RPN_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TRAIN.RPN_POST_NMS_TOP_N,
            threshold=config.TRAIN.RPN_NMS_THRESH, rpn_min_size=config.TRAIN.RPN_MIN_SIZE)
    else:
        rois = mx.symbol.Custom(
            cls_prob=rpn_cls_act_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois',
            op_type='proposal', feat_stride=config.RPN_FEAT_STRIDE,
            scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
            rpn_pre_nms_top_n=config.TRAIN.RPN_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TRAIN.RPN_POST_NMS_TOP_N,
            threshold=config.TRAIN.RPN_NMS_THRESH, rpn_min_size=config.TRAIN.RPN_MIN_SIZE)

    # ROI proposal target
    gt_boxes_reshape = mx.symbol.Reshape(data=gt_boxes, shape=(-1, 5), name='gt_boxes_reshape')
    group = mx.symbol.Custom(rois=rois, gt_boxes=gt_boxes_reshape, op_type='proposal_target',
                             num_classes=num_classes, batch_images=config.TRAIN.BATCH_IMAGES,
                             batch_rois=config.TRAIN.BATCH_ROIS, fg_fraction=config.TRAIN.FG_FRACTION)
    rois = group[0]
    label = group[1]
    bbox_target = group[2]
    bbox_weight = group[3]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



example/rcnn/rcnn/symbol/symbol_vgg.py [336:380]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    rpn_relu = mx.symbol.Activation(data=rpn_conv, act_type="relu", name="rpn_relu")
    rpn_cls_score = mx.symbol.Convolution(
        data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=2 * num_anchors, name="rpn_cls_score")
    rpn_bbox_pred = mx.symbol.Convolution(
        data=rpn_relu, kernel=(1, 1), pad=(0, 0), num_filter=4 * num_anchors, name="rpn_bbox_pred")

    # prepare rpn data
    rpn_cls_score_reshape = mx.symbol.Reshape(
        data=rpn_cls_score, shape=(0, 2, -1, 0), name="rpn_cls_score_reshape")

    # classification
    rpn_cls_prob = mx.symbol.SoftmaxOutput(data=rpn_cls_score_reshape, label=rpn_label, multi_output=True,
                                           normalization='valid', use_ignore=True, ignore_label=-1, name="rpn_cls_prob")
    # bounding box regression
    rpn_bbox_loss_ = rpn_bbox_weight * mx.symbol.smooth_l1(name='rpn_bbox_loss_', scalar=3.0, data=(rpn_bbox_pred - rpn_bbox_target))
    rpn_bbox_loss = mx.sym.MakeLoss(name='rpn_bbox_loss', data=rpn_bbox_loss_, grad_scale=1.0 / config.TRAIN.RPN_BATCH_SIZE)

    # ROI proposal
    rpn_cls_act = mx.symbol.SoftmaxActivation(
        data=rpn_cls_score_reshape, mode="channel", name="rpn_cls_act")
    rpn_cls_act_reshape = mx.symbol.Reshape(
        data=rpn_cls_act, shape=(0, 2 * num_anchors, -1, 0), name='rpn_cls_act_reshape')
    if config.TRAIN.CXX_PROPOSAL:
        rois = mx.contrib.symbol.Proposal(
            cls_prob=rpn_cls_act_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois',
            feature_stride=config.RPN_FEAT_STRIDE, scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
            rpn_pre_nms_top_n=config.TRAIN.RPN_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TRAIN.RPN_POST_NMS_TOP_N,
            threshold=config.TRAIN.RPN_NMS_THRESH, rpn_min_size=config.TRAIN.RPN_MIN_SIZE)
    else:
        rois = mx.symbol.Custom(
            cls_prob=rpn_cls_act_reshape, bbox_pred=rpn_bbox_pred, im_info=im_info, name='rois',
            op_type='proposal', feat_stride=config.RPN_FEAT_STRIDE,
            scales=tuple(config.ANCHOR_SCALES), ratios=tuple(config.ANCHOR_RATIOS),
            rpn_pre_nms_top_n=config.TRAIN.RPN_PRE_NMS_TOP_N, rpn_post_nms_top_n=config.TRAIN.RPN_POST_NMS_TOP_N,
            threshold=config.TRAIN.RPN_NMS_THRESH, rpn_min_size=config.TRAIN.RPN_MIN_SIZE)

    # ROI proposal target
    gt_boxes_reshape = mx.symbol.Reshape(data=gt_boxes, shape=(-1, 5), name='gt_boxes_reshape')
    group = mx.symbol.Custom(rois=rois, gt_boxes=gt_boxes_reshape, op_type='proposal_target',
                             num_classes=num_classes, batch_images=config.TRAIN.BATCH_IMAGES,
                             batch_rois=config.TRAIN.BATCH_ROIS, fg_fraction=config.TRAIN.FG_FRACTION)
    rois = group[0]
    label = group[1]
    bbox_target = group[2]
    bbox_weight = group[3]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -