本文整理汇总了Python中cntk.layers方法的典型用法代码示例。如果您正苦于以下问题：Python cntk.layers方法的具体用法？Python cntk.layers怎么用？Python cntk.layers使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类cntk的用法示例。
在下文中一共展示了cntk.layers方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: create_faster_rcnn_predictor
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import layers [as 别名]
def create_faster_rcnn_predictor(base_model_file_name, features, scaled_gt_boxes, dims_input):
# Load the pre-trained classification net and clone layers
base_model = load_model(base_model_file_name)
conv_layers = clone_conv_layers(base_model)
fc_layers = clone_model(base_model, [pool_node_name], [last_hidden_node_name], clone_method=CloneMethod.clone)
# Normalization and conv layers
feat_norm = features - normalization_const
conv_out = conv_layers(feat_norm)
# RPN and prediction targets
rpn_rois, rpn_losses = \
create_rpn(conv_out, scaled_gt_boxes, dims_input, proposal_layer_param_string=cfg["CNTK"].PROPOSAL_LAYER_PARAMS)
rois, label_targets, bbox_targets, bbox_inside_weights = \
create_proposal_target_layer(rpn_rois, scaled_gt_boxes, num_classes=globalvars['num_classes'])
# Fast RCNN and losses
cls_score, bbox_pred = create_fast_rcnn_predictor(conv_out, rois, fc_layers)
detection_losses = create_detection_losses(cls_score, label_targets, rois, bbox_pred, bbox_targets, bbox_inside_weights)
loss = rpn_losses + detection_losses
pred_error = classification_error(cls_score, label_targets, axis=1)
return loss, pred_error