markdown test

## tf.nn.
- conv2d
```
conv2d(
    input,      shape[batch, in_height, in_width, in_channels]
    filter,      shape[filter_height, filter_width, in_channels, out_channels]
    strides,
    padding,
    use_cudnn_on_gpu=True,
    data_format='NHWC',
    dilations=[1, 1, 1, 1],
    name=None
)
```
```
Computes a 2-D convolution given 4-D input and filter tensors.
Given an input tensor of shape [batch, in_height, in_width, in_channels] and a filter / kernel tensor of shape[filter_height, filter_width, in_channels, out_channels], this op performs the following:

1.Flattens the filter to a 2-D matrix with shape [filter_height * filter_width * in_channels, output_channels].

2.Extracts image patches from the input tensor to form a virtual tensor of shape [batch, out_height, out_width, filter_height * filter_width * in_channels].

3.For each patch, right-multiplies the filter matrix and the image patch vector.
In detail, with the default NHWC format,
output[b, i, j, k] =
    sum_{di, dj, q} input[b, strides[1] * i + di, strides[2] * j + dj, q] *
                    filter[di, dj, q, k]
Must have strides[0] = strides[3] = 1. For the most common case of the same horizontal and vertices strides, strides = [1, stride, stride, 1].
```

- moments
```
Calculate the mean and variance of x
```
- batch_normalization
```
Normalizes a tensor by mean and variance, and applies (optionally) a scale γ to it, as well as an offset β:
```
- max_pool
- embedding_lookup
- l2_loss
- bias_add

- relu

- dropout

- xw_plus_b

- softmax_cross_entropy_with_logits_v2

## tf
- random_uniform
```
Returns:
A tensor of the specified shape filled with random uniform values.
```
- expand_dims
```
Inserts a dimension of 1 into a tensor's shape.
name_scope
```
- truncated_normal
```
tf.truncated_normal(shape, mean, stddev) :shape表示生成张量的维度，mean是均值，stddev是标准差。这个函数产生正太分布，均值和标准差自己设定。这是一个截断的产生正太分布的函数，就是说产生正太分布的值如果与均值的差值大于两倍的标准差，那就重新生成。和一般的正太分布的产生随机数据比起来，这个函数产生的随机数与均值的差距不会超过两倍的标准差，但是一般的别的函数是可能的。
```
- constant
```
value参数可以是一个常量值，或者一个dtype类型的值列表。如果value为一个列表，那么这个列表的长度必须小于或等于shape参数所指定的大小(如果设置shape的话)。当列表长度小于shape参数所指定的大小时，缺少的列表项会被填充为列表的最后一个参数。
shape参数是可选的。如果存在该参数，它会指明生成的张量的维度。如果不存在，则使用value的shape。
```
- argmax
```
Returns the index with the largest value across axes of a tensor. (deprecated arguments)
```
- Variable
- concat
- reshape
- placeholder
```
Inserts a placeholder for a tensor that will be always fed.
Important: This tensor will produce an error if evaluated. Its value must be fed using the feed_dict optional argument to Session.run(), Tensor.eval(), or Operation.run().
For example:
x = tf.placeholder(tf.float32, shape=(1024, 1024))
y = tf.matmul(x, x)

with tf.Session() as sess:
  print(sess.run(y))  # ERROR: will fail because x was not fed.

  rand_array = np.random.rand(1024, 1024)
  print(sess.run(y, feed_dict={x: rand_array}))  # Will succeed.
```
- equal
```
Returns the truth value of (x == y) element-wise.
```
- reduce_mean
```
x = tf.constant([[1, 1, 1], [1, 1, 1]])
tf.reduce_sum(x)  # 6
tf.reduce_sum(x, 0)  # [2, 2, 2]
tf.reduce_sum(x, 1)  # [3, 3]
tf.reduce_sum(x, 1, keepdims=True)  # [[3], [3]]
tf.reduce_sum(x, [0, 1])  # 6
```
- cast
```
转换类型
```