tensorflow - 使用 keras Convolutional1D Layer 时出现负维度错误

Question

我正在尝试使用 Keras 创建一个 char cnn。这种类型的 cnn 要求您使用 Convolutional1D 层。但我尝试将它们添加到模型中的所有方法，都会在创建阶段给我带来错误。这是我的代码:

def char_cnn(n_vocab, max_len, n_classes):
    conv_layers = [[256, 7, 3],
                   [256, 7, 3],
                   [256, 3, None],
                   [256, 3, None],
                   [256, 3, None],
                   [256, 3, 3]]
    fully_layers = [1024, 1024]
    th = 1e-6

    embedding_size = 128

    inputs = Input(shape=(max_len,), name='sent_input', dtype='int64')

    # Embedding layer

    x = Embedding(n_vocab, embedding_size, input_length=max_len)(inputs)

    # Convolution layers
    for cl in conv_layers:
        x = Convolution1D(cl[0], cl[1])(x)
        x = ThresholdedReLU(th)(x)
        if not cl[2] is None:
            x = MaxPooling1D(cl[2])(x)


    x = Flatten()(x)


    #Fully connected layers

    for fl in fully_layers:
        x = Dense(fl)(x)
        x = ThresholdedReLU(th)(x)
        x = Dropout(0.5)(x)


    predictions = Dense(n_classes, activation='softmax')(x)

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

    model.compile(optimizer='adam', loss='categorical_crossentropy')

    return model

这是我尝试调用 char_cnn 函数时收到的错误

InvalidArgumentError                      Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, require_shape_fn)
    685           graph_def_version, node_def_str, input_shapes, input_tensors,
--> 686           input_tensors_as_shapes, status)
    687   except errors.InvalidArgumentError as err:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    515             compat.as_text(c_api.TF_Message(self.status.status)),
--> 516             c_api.TF_GetCode(self.status.status))
    517     # Delete the underlying status object from memory otherwise it stays alive

InvalidArgumentError: Negative dimension size caused by subtracting 3 from 1 for 'conv1d_26/convolution/Conv2D' (op: 'Conv2D') with input shapes: [?,1,1,256], [1,3,256,256].

如何解决？

Answer 1

您的下采样过于激进，这里的关键参数是 max_len:当它太小时，序列会变得太短而无法执行卷积或最大池化。您设置了 pool_size=3，因此它会在每次池化后将序列缩小 3 倍(请参见下面的示例)。我建议您尝试 pool_size=2。

此网络可以处理的最小 max_len 是 max_len=123。在本例中，x 形状按以下方式转换(根据 conv_layers):

(?, 123, 128)
(?, 39, 256)
(?, 11, 256)
(?, 9, 256)
(?, 7, 256)
(?, 5, 256)

设置较小的值，例如 max_len=120 会导致 x.shape=(?, 4, 256) 在最后一层之前，并且无法执行此操作。