> For the complete documentation index, see [llms.txt](https://baozoulin.gitbook.io/tensorflow/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://baozoulin.gitbook.io/tensorflow/jian-zao-di-yi-ge-shen-jing-wang-luo/tian-jia-ceng-def-add-layer.md).

# 添加层 def add\_layer()

神经层里常见的参数通常有**weights**、**biases**和**激励函数**

**weights**为一个**in\_size**行, **out\_size**列的随机变量矩阵

**biases**的推荐值不为0，在0向量的基础上加**0.1**

**Wx\_plus\_b**, 即神经网络未激活的值

```python
import tensorflow as tf

def add_layer(inputs, in_size, out_size, activation_function=None): 

    Weights = tf.Variable(tf.random_normal([in_size, out_size])) 
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs
```

更新为：

```python
tf.layers.dense(
    inputs,
    units,
    activation=None,
    use_bias=True,
    kernel_initializer=None,
    bias_initializer=tf.zeros_initializer(),
    kernel_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    kernel_constraint=None,
    bias_constraint=None,
    trainable=True,
    name=None,
    reuse=None
)
```