“顺序模型的第一层必须获得一个“ inputShape”或“ batchInputShape”参数。”使用TensorFlow.js加载Keras模型时

Question

我使用Keras（版本2.2.4）训练了以下模型：

# imports ...
model = Sequential()
model.add(Conv2D(filters=64, kernel_size=5, data_format="channels_last", activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(data_format="channels_last"))
model.add(Conv2D(filters=32, kernel_size=3, data_format="channels_last", activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(data_format="channels_last"))
model.add(Flatten(data_format="channels_last"))
model.add(Dense(units=256, activation="relu"))
model.add(Dense(units=128, activation="relu"))
model.add(Dense(units=32, activation="relu"))
model.add(Dense(units=8, activation="softmax"))
# training ...
model.save("model.h5")

输入是形状为(28, 28, 1)的28 x 28灰度图像。

我使用tensorflowjs_converter转换了模型，现在我想使用TensorFlow.js（版本1.1.0）将其加载到我的网站中：

tf.loadLayersModel('./model/model.json')

这会产生以下错误：

The first layer in a Sequential model must get an `inputShape` or `batchInputShape` argument.
    at new e (errors.ts:48)
    at e.add (models.ts:440)
    at e.fromConfig (models.ts:1020)
    at vp (generic_utils.ts:277)
    at nd (serialization.ts:31)
    at models.ts:299
    at common.ts:14
    at Object.next (common.ts:14)
    at o (common.ts:14)

如何在不重新训练模型的情况下解决此错误？

Answer 1

尝试将神经网络调整为以下格式：

input_img = Input(batch_shape=(None, 28,28,1))
layer1=Conv2D(filters=64, kernel_size=5, data_format="channels_last", activation="relu")(input_img)
layer2=BatchNormalization()(layer1)
.
.
.
final_layer=Dense(units=8, activation="softmax")(previous_layer)

...等等。最后：

model = Model(inputs = input_img, outputs = final_layer)

Answer 2

您必须在keras模型的Conv2D层中指定输入形状。

# imports ...
model = Sequential()
model.add(Conv2D(input_shape=(28, 28, 1), filters=64, kernel_size=5, data_format="channels_last", activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(data_format="channels_last"))
model.add(Conv2D(filters=32, kernel_size=3, data_format="channels_last", activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(data_format="channels_last"))
model.add(Flatten(data_format="channels_last"))
model.add(Dense(units=256, activation="relu"))
model.add(Dense(units=128, activation="relu"))
model.add(Dense(units=32, activation="relu"))
model.add(Dense(units=8, activation="softmax"))
# training ...
model.save("model.h5")

Answer 3

最好的方法是更改​​您的keras模型并重新训练。

无论如何，如果您不能重新训练网络，则可以手动编辑model.json文件。

您需要在model.json文件中找到输入层并添加

  "config": {
    ...
    "batch_input_shape": [
      null,
      28,
      28,
      1
    ]
    ...
  }