Question

我正在尝试构建一个模型来着色图像。我正在使用LAB色彩空间。模型的输入是L通道，并且要训练模型以预测A和B通道。我希望通过几个卷积运行L通道，然后将其拆分为另外两个独立计算A和B通道的模型。最后，我想将它们合并在一起以获得输出。

<nav class="navbar navbar-inverse navbar-fixed-top my-navbar">
  <div class="container">
    <!-- Brand and toggle get grouped for better mobile display -->
    <div class="navbar-header">
      <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1" aria-expanded="false">
        <span class="sr-only">Toggle navigation</span>
        <span class="icon-bar"></span>
        <span class="icon-bar"></span>
        <span class="icon-bar"></span>
      </button>
      <a class="navbar-brand" href="/boyt2">Company Name</a>
    </div>
    <!-- Collect the nav links, forms, and other content for toggling -->
    <div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1">
      <ul class="nav navbar-nav">
        <li><a href="#">&bull;&nbsp; Link 1<span class="sr-only">(current)</span></a></li>
        <li><a href="#">Link 2</a></li>
        <li>
            <form class="navbar-form navbar-left searchsite" role="search">
                <div class="form-group">
                    <input type="text" class="form-control" placeholder="Search">
                </div>
                    <button type="submit" class="btn btn-default">Submit</button>
            </form>
        </li>
      </ul>
      <ul class="nav navbar-nav navbar-right">
        <li class="dropdown">
          <a href="#" class="dropdown-toggle avatar" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Username <span class="caret"></span> &nbsp; <img src="http://placehold.it/30x30"></a>
          <ul class="dropdown-menu noshadow">
            <li><a href="#">Action</a></li>
            <li><a href="#">Another action</a></li>
            <li><a href="#">Something else here</a></li>
            <li role="separator" class="divider"></li>
            <li><a href="#">Separated link</a></li>
          </ul>
        </li>
      </ul>
    </div><!-- /.navbar-collapse -->
  </div><!-- /.container-fluid -->
</nav>






<!-- JavaScript files should be linked at the bottom of the page -->
<script src="js/jquery.min.js"></script>

<!-- Latest compiled and minified Javascript -->
<script src="js/bootstrap.min.js"></script>

当我尝试创建合并图层时出现以下错误。

model = Sequential()
model.add(InputLayer((1, H, W)))

model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
last = Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu')
model.add(last)

a_model = Sequential()
a_model.add(last)
a_model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
a_model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
a_model.add(Convolution2D(1, 3, 3, border_mode = 'same', activation = 'sigmoid'))

b_model = Sequential()
b_model.add(last)
b_model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
b_model.add(Convolution2D(64, 5, 5, border_mode = 'same', activation = 'relu'))
b_model.add(Convolution2D(1, 3, 3, border_mode = 'same', activation = 'sigmoid'))

model.add(Merge((a_model, b_model), mode = 'concat'))

我希望模型的外观为（2，H，W），其中H和W是图像的高度和宽度。

Answer 1

Sequential模型不允许您在网络中创建分支。请改用功能API（Keras 1.0中的新功能）。您可以关注this tutorial。

合并层的Keras错误

1 个答案: