tf.nn.relu()--修正线性单元函数

参考官方文档

format：relu(features, name=None)

Args：features: A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `int64`, `uint8`, `int16`, `int8`, `uint16`, `half`.

        name: A name for the operation (optional).

return： A `Tensor`. Has the same type as `features`.

relu： Computes rectified linear: `max(features, 0)`也就是说relu的功能是将输入的feature的tensor所有的元素中如果小于零的就取零。