函数定义 @tf_export('layers.flatten') def flatten(inputs, name=None): """Flattens an input tensor while preserving the batch axis (axis 0). 保留axis(axis0)的同时平移输入张量,即把一个输入大小为n*h*w的Tensor变成n*(hw),相当于reshape特殊操作 Arguments: inputs: Tensor input. name: The name of the layer (string). Returns: