Question

这有效：

img = Input(shape=(224,224,3))

efnet = EfficientNetB0(

    weights = 'noisy-student',
    include_top = False,
    pooling = None,
    classes = None

)
for layer in efnet.layers:
    layer.trainable = False

x = efnet(img)
# ... any number of layers ...
x = Dense(1)(x)

model = Model(inputs=img, outputs=x)

这不是（“图形已断开连接”）：

img = Input(shape=(224,224,3))
img = Dropout(0.2)(img)
# ^ "Preprocessing" could be anything, Dropout is a simple example

efnet = EfficientNetB0(

    weights = 'noisy-student',
    include_top = False,
    pooling = None,
    classes = None

)
for layer in efnet.layers:
    layer.trainable = False

x = efnet(img)
# ... any number of layers ... 
x = Dense(1)(x)

model = Model(inputs=img, outputs=x)

两者之间的唯一区别是“预处理”。为什么这种方法不起作用，如何将中间层放置在输入和如上所示的“模型作为图层”之间？

（在efnet声明中指定input_shape和/或input_tensor无效。实际上，指定input_tensor神秘地导致efnet权重无法加载，因为efnet显然具有131层（???）而不是预期为130。）

Answer 1

我找到了解决该问题的方法，尽管我不知道为什么该方法会有所不同。

这有效：

<!DOCTYPE html>
<html lang="en">

<head>
  <title>Title</title>
  <meta charset="utf-8">
  <meta name="viewport" content="width=device-width, initial-scale=1">
  <link rel="shortcut icon" href="favicon.gif" type="image/x-icon" />
  <link rel="icon" href="favicon.gif" type="image/xIicon" />
  <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.4.1/css/bootstrap.min.css">
  <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.7.0/css/all.css" integrity="sha384-lZN37f5QGtY3VHgisS14W3ExzMWZxybE1SJSEsQp9S+oqd12jhcu+A56Ebc1zFSJ" crossorigin="anonymous">
  <link href="https://fonts.googleapis.com/css?family=Lato:400,700&display=swap" rel="stylesheet">
  <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js"></script>
  <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.16.0/umd/popper.min.js"></script>
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/4.4.1/js/bootstrap.min.js"></script>
  <script src="https://kit.fontawesome.com/de6f7ac358.js" crossorigin="anonymous"></script>
</head>

<body>
  <div class="small-nav-dropdown-menu">
    <ul style="background-color: rgb(36, 204, 151);">
      <li>
        <a href="#">
          <span style="color: #fff">Menu 1</span>
        </a>
        <ul class="a-new-class" style="background-color: #00bc92;">
          <li>
            <a href="#">
              <span class="main-nav-dropdown-item-text">1.1</span>
            </a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">1.2</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">1.3</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">1.4</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">1.5</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">1.6</a>
          </li>
          <li>
            <a href="#">
              <span class="main-nav-dropdown-item-text">1.7</span>
            </a>
          </li>
          <li>
            <a>
              <span class="main-nav-dropdown-item-text">1.8</span>
            </a>
          </li>
        </ul>
      </li>
      <li>
        <a href="#">
          <span style="color: #fff">Menu 2</span>
        </a>
        <ul class="a-new-class" style="background-color: #00bc92;">
          <li>
            <a href="#">
              <span class="main-nav-dropdown-item-text">2.1</span>
            </a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">2.2</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">2.3</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">2.4</a>
          </li>
          <li>
            <a href="#" class="main-nav-dropdown-item-text">2.5</a>
          </li>
          <li>
            <a href="#">
              <span class="main-nav-dropdown-item-text">2.6</span>
            </a>
          </li>
          <li>
            <a href="#">
              <span class="main-nav-dropdown-item-text">2.7</span>
            </a>
          </li>
        </ul>
      </li>
    </ul>
  </div>
</body>

</html>

这不是：

img = Input(shape=(224,224,3))
x = Dropout(0.2)(img)
x = efnet(x) 
x = Dense(1)(x)
model = Model(inputs=img, outputs=x)

如何在输入图层和“模型图层”之间放置图层？

1 个答案: