0

我想在 TF2 中构建一个模型，它由以下组件组成：MobilenetV2, 2 层，BLSTM然后CTC附加到它。下面演示了该模型：

def build_model():
    img_width = 200
    img_height = 50

    input_img = layers.Input(shape=(img_width, img_height, 3), name="input_1", dtype="float32")

    labels = layers.Input(name="label", shape=(None,), dtype="float32")

    base_model=tf.keras.applications.MobileNet(
        input_shape=(img_width, img_height, 3),
        alpha=1.0,
        depth_multiplier=1,
        dropout=0.001,
        include_top=False,
        weights="imagenet",
        input_tensor=None,
        pooling=None,
        classes=1000,
        classifier_activation="softmax",
    )
    x = base_model.output
    x = layers.Reshape(target_shape=(6,1024), name="reshape")(x)
    x = Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)
    x = Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)
    output = CTCLayer(name="ctc_loss")(labels, x)
    
    # Define the model
    model = keras.models.Model(
        inputs=[base_model.input, labels], outputs=output, name="ocr_model_v1"
    )
    # Optimizer
    opt = keras.optimizers.Adam()
    # Compile the model and return
    model.compile(optimizer=opt)
    return model

当我调用该build_model函数时，它会引发以下错误：

ValueError：输入“input_1”缺少数据。您传递了一个带有键 ['image', 'label'] 的数据字典。需要以下键：['input_1', 'label']

知道如何解决吗？

4

0 回答 0