1.如何理解 tf.reduce_max或者 tf.reduce_mean中对Tensor和高维矩阵的坐标轴axis的选择的操作 tf.reduce_mean( input_tensor, axis=None, keepdims=None, name=None, reduction_indices=None, keep_dims=None ) x = tf.constant([[1., 1.], [2., 2.]]) tf.reduce_mean(x) # 1.5 tf.reduce_mean(