未验证 提交 4416990b 编写于 作者: F FlyingQianMM 提交者: GitHub

test=document_preview (#1500)

change the output of retinanet_target_assign in api_cn
上级 93cb7fad
......@@ -68,6 +68,6 @@ retinanet_target_assign
dtype='float32')
im_info = fluid.data(name='im_info', shape=[1, 3],
dtype='float32')
loc_pred, score_pred, loc_target, score_target, bbox_inside_weight, fg_num =
score_pred, loc_pred, score_target, loc_target, bbox_inside_weight, fg_num =
fluid.layers.retinanet_target_assign(bbox_pred, cls_logits, anchor_box,
anchor_var, gt_boxes, gt_labels, is_crowd, im_info, 10)
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册