Question

我正在尝试将文章“从零开始的文字理解”的方法应用到不同的数据集。我很难让我的模型运行。

我的句子变成了Tensor of shape

(19579, 140, 69)

我已经使用以下方法预处理我的目标：

lb = sklearn.preprocessing.LabelBinarizer()
lb.fit(authors)
targets = lb.transform(authors)
targets = targets.reshape((targets.shape[0], 1, targets.shape[1]))

以

形式出现

(19579, 1, 3)

张量

我的模特是：

nb_filter = 256
dense_outputs = 1024
cat_output = 3
batch_size = 80
nb_epoch = 10
inputs = Input(shape=(maxlen, vocab_size), name='input', dtype='float32')
conv0 = Convolution1D(nb_filter=nb_filter, filter_length=18, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(inputs)
conv0 = MaxPooling1D(pool_length=2)(conv0)

conv1 = Convolution1D(nb_filter=nb_filter, filter_length=14, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv0)
conv1 = MaxPooling1D(pool_length=2)(conv1)

conv2 = Convolution1D(nb_filter=nb_filter, filter_length=4, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv1)

conv3 = Convolution1D(nb_filter=nb_filter, filter_length=4, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv2)

conv4 = Convolution1D(nb_filter=nb_filter, filter_length=4, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv3)

conv5 = Convolution1D(nb_filter=nb_filter, filter_length=4, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv4)

conv6 = Convolution1D(nb_filter=nb_filter, filter_length=4, border_mode='valid', activation='relu', input_shape=(maxlen, vocab_size))(conv5)
conv6 = MaxPooling1D(pool_length=2)(conv6)

dense0 = Dropout(0.5)(Dense(dense_outputs, activation='relu')(conv6))
dense1 = Dropout(0.5)(Dense(dense_outputs, activation='relu')(dense0))

pred = Dense(cat_output, activation='softmax', name='output')(dense1)

model = Model(input=inputs, output=pred)

sgd = SGD(lr=0.01, momentum=0.9)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

但是当我打电话时

model.fit(x=X_train, y=y_train)

我收到以下错误：

ValueError: Error when checking target: expected output to have shape (None, 5, 3) but got array with shape (15663, 1, 3)

我意识到我没有正确预处理目标，但我无法弄清楚到底发生了什么！

Answer 1

模型输出的形状（(None, 5, 3)）必须等于目标数据的形状（(None, 1, 3)）。

您输入了(None, maxlen, vocab_size)之类的输入您的卷积图层和合并图层将maxlen减少到最终值5.（请参阅model.summary()以了解您的形状发生了什么）。

你必须找到一种方法将这5变为1.有几种可能性。

在密集层之前添加GlobalMaxPooling1D或GlobalAveragePooling1D。
Flatten() Dense图层之前的数据。

转换Keras CNN的文本

1 个答案: