设置Keras.backend.ctc_batch_cost的标志

编程问答 2022-06-05

问题描述

目前，对于大多数数据而言，我的单词识别神经网络非常有效。但是对于某些人，我遇到了这个错误。

没有足够的时间完成目标转换序列（必填：53，可用：50）0您可以使用标志ignore_longer_outputs_than_inputs将此错误变成警告

我对此进行了调查，并了解到我必须设置标志ignore_longer_outputs_than_inputs，但是我无法弄清位置。这是我的模型的代码。

    def __init__(self,name=None):
        super().__init__(name=name)
        self.loss_fn = keras.backend.ctc_batch_cost

    def call(self,y_true,y_pred):
        # Compute the training-time loss value and add it
        # to the layer using `self.add_loss()`.
        batch_len = tf.cast(tf.shape(y_true)[0],dtype="int64")
        input_length = tf.cast(tf.shape(y_pred)[1],dtype="int64")
        label_length = tf.cast(tf.shape(y_true)[1],dtype="int64")

        input_length = input_length * tf.ones(shape=(batch_len,1),dtype="int64")
        label_length = label_length * tf.ones(shape=(batch_len,dtype="int64")

        loss = self.loss_fn(y_true,y_pred,input_length,label_length)
        self.add_loss(loss)

        # At test time,just return the computed predictions
        return y_pred


def build_model():
    # Inputs to the model
    input_img = layers.Input(
        shape=(img_width,img_height,name="image",dtype="float32"
    )
    labels = layers.Input(name="label",shape=(None,),dtype="float32")

    # First conv block
    x = layers.Conv2D(
        32,(3,3),activation="relu",kernel_initializer="he_normal",padding="same",name="Conv1",)(input_img)
    x = layers.MaxPooling2D((2,2),name="pool1")(x)

    # Second conv block
    x = layers.Conv2D(
        64,name="Conv2",)(x)
    x = layers.MaxPooling2D((2,name="pool2")(x)

    # We have used two max pool with pool size and strides 2.
    # Hence,downsampled feature maps are 4x smaller. The number of
    # filters in the last layer is 64. Reshape accordingly before
    # passing the output to the RNN part of the model
    new_shape = ((img_width // 4),(img_height // 4) * 64)
    x = layers.Reshape(target_shape=new_shape,name="reshape")(x)
    x = layers.Dense(64,name="dense1")(x)
    x = layers.Dropout(0.2)(x)

    # RNNs
    x = layers.Bidirectional(layers.LSTM(128,return_sequences=True,dropout=0.25))(x)
    x = layers.Bidirectional(layers.LSTM(64,dropout=0.25))(x)

    # Output layer
    x = layers.Dense(len(characters) + 1,activation="softmax",name="dense2")(x)

    # Add CTC layer for calculating CTC loss at each step
    output = CTCLayer(name="ctc_loss")(labels,x)

    # Define the model
    model = keras.models.Model(
        inputs=[input_img,labels],outputs=output,name="ocr_model_v1",ignore_longer_outputs_than_inputs=True
    )
    # Optimizer
    opt = keras.optimizers.Adam()
    # Compile the model and return
    model.compile(optimizer=opt)
    return model

我想我将其放在下面的行中，但这似乎不起作用。 Keras.backend不允许您设置标志吗？

loss = self.loss_fn(y_true,label_length)

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）

ctckeraskeras