假设图像shape=(dim_x, dim_y, img_channels)，您可以通过设置以下内容获得1D卷积:

Assuming that your image shape=(dim_x, dim_y, img_channels) you can obtain a 1D convolution by setting:

conv1d_on_image = Convolution2D(output_channels, 1, dim_y, border_mode='valid')(input)

请记住，此层的输出将具有形状(dim_x, 1, output_channels).如果您希望输入是连续的，则可以通过设置以下内容来使用Reshape层:

Remember that the output from this layer would have shape (dim_x, 1, output_channels). If you want your input to be sequential you may use the Reshape layer by setting:

conv1d_on_image = Reshape((dim_x, output_channels))(conv1d_on_image)

这将产生形状为(dim_x, output_channels)的输出.

This would produce output with shape (dim_x, output_channels).

一个有趣的事实是，这正是Conv1D在具有tf后端的Keras中工作的方式.

An interesting fact is that this is exactly the way how Conv1D works in Keras with tf backend.