在查看代碼的時(shí)候炉抒，看到有代碼用到卷積層是tf.nn.conv2d梁棠，但是也有的使用的卷積層是tf.contrib.slim.conv2d靠闭，這兩個(gè)函數(shù)調(diào)用的卷積層是否一致，在查看了API的文檔塞琼，以及slim.conv2d的源碼后菠净，做如下總結(jié)：
首先是常見使用的tf.nn.conv2d的函數(shù)，其定義如下：

conv2d(
    input,
    filter,
    strides,
    padding,
    use_cudnn_on_gpu=None,
    data_format=None,
    name=None
)

input指需要做卷積的輸入圖像彪杉，它要求是一個(gè)Tensor毅往，具有[batch_size, in_height, in_width, in_channels]這樣的shape，具體含義是[訓(xùn)練時(shí)一個(gè)batch的圖片數(shù)量, 圖片高度, 圖片寬度, 圖像通道數(shù)]派近，注意這是一個(gè)4維的Tensor攀唯，要求數(shù)據(jù)類型為float32和float64其中之一
filter用于指定CNN中的卷積核，它要求是一個(gè)Tensor渴丸，具有[filter_height, filter_width, in_channels, out_channels]這樣的shape侯嘀，具體含義是[卷積核的高度，卷積核的寬度谱轨，圖像通道數(shù)戒幔，卷積核個(gè)數(shù)]，要求類型與參數(shù)input相同土童，有一個(gè)地方需要注意诗茎，第三維in_channels，就是參數(shù)input的第四維献汗，這里是維度一致敢订，不是數(shù)值一致罢吃。這里out_channels指定的是卷積核的個(gè)數(shù)楚午，而in_channels說明卷積核的維度與圖像的維度一致，在做卷積的時(shí)候刃麸，單個(gè)卷積核在不同維度上對(duì)應(yīng)的卷積圖片糟袁，然后將in_channels個(gè)通道上的結(jié)果相加，加上bias來得到單個(gè)卷積核卷積圖片的結(jié)果讹剔。
strides為卷積時(shí)在圖像每一維的步長(zhǎng)都哭，這是一個(gè)一維的向量，長(zhǎng)度為4吁伺，對(duì)應(yīng)的是在input的4個(gè)維度上的步長(zhǎng)
padding是string類型的變量饮睬，只能是"SAME","VALID"其中之一，這個(gè)值決定了不同的卷積方式篮奄，SAME代表卷積核可以停留圖像邊緣捆愁，VALID表示不能割去，更詳細(xì)的描述可以參考http://blog.csdn.net/mao_xiao_feng/article/details/53444333
use_cudnn_on_gpu指定是否使用cudnn加速，默認(rèn)為true
data_format是用于指定輸入的input的格式昼丑，默認(rèn)為NHWC格式

結(jié)果返回一個(gè)Tensor呻逆，這個(gè)輸出，就是我們常說的feature map

而對(duì)于tf.contrib.slim.conv2d菩帝，其函數(shù)定義如下：

convolution(inputs,
          num_outputs,
          kernel_size,
          stride=1,
          padding='SAME',
          data_format=None,
          rate=1,
          activation_fn=nn.relu,
          normalizer_fn=None,
          normalizer_params=None,
          weights_initializer=initializers.xavier_initializer(),
          weights_regularizer=None,
          biases_initializer=init_ops.zeros_initializer(),
          biases_regularizer=None,
          reuse=None,
          variables_collections=None,
          outputs_collections=None,
          trainable=True,
          scope=None):

inputs同樣是指需要做卷積的輸入圖像
num_outputs指定卷積核的個(gè)數(shù)（就是filter的個(gè)數(shù)）
kernel_size用于指定卷積核的維度（卷積核的寬度咖城，卷積核的高度）
stride為卷積時(shí)在圖像每一維的步長(zhǎng)
padding為padding的方式選擇，VALID或者SAME
data_format是用于指定輸入的input的格式
rate這個(gè)參數(shù)不是太理解呼奢，而且tf.nn.conv2d中也沒有宜雀，對(duì)于使用atrous convolution的膨脹率（不是太懂這個(gè)atrous convolution）
activation_fn用于激活函數(shù)的指定，默認(rèn)的為ReLU函數(shù)
normalizer_fn用于指定正則化函數(shù)
normalizer_params用于指定正則化函數(shù)的參數(shù)
weights_initializer用于指定權(quán)重的初始化程序
weights_regularizer為權(quán)重可選的正則化程序
biases_initializer用于指定biase的初始化程序
biases_regularizer: biases可選的正則化程序
reuse指定是否共享層或者和變量
variable_collections指定所有變量的集合列表或者字典
outputs_collections指定輸出被添加的集合
trainable:卷積層的參數(shù)是否可被訓(xùn)練
scope:共享變量所指的variable_scope

在上述的API中握础，可以看出去除掉初始化的部分辐董，那么兩者并沒有什么不同，只是tf.contrib.slim.conv2d提供了更多可以指定的初始化的部分禀综，而對(duì)于tf.nn.conv2d而言简烘，其指定filter的方式相比較tf.contrib.slim.conv2d來說，更加的復(fù)雜菇存。去除掉少用的初始化部分夸研，其實(shí)兩者的API可以簡(jiǎn)化如下：

tf.contrib.slim.conv2d (inputs,
                num_outputs,[卷積核個(gè)數(shù)]
                kernel_size,[卷積核的高度，卷積核的寬度]
                stride=1,
                padding='SAME',
)
tf.nn.conv2d(
    input,(與上述一致)
    filter,([卷積核的高度依鸥，卷積核的寬度亥至，圖像通道數(shù)，卷積核個(gè)數(shù)])
    strides,
    padding,
)

可以說兩者是幾乎相同的贱迟，運(yùn)行下列代碼也可知這兩者一致

import tensorflow as tf 
import tensorflow.contrib.slim as slim
 
x1 = tf.ones(shape=[1, 64, 64, 3]) 
w = tf.fill([5, 5, 3, 64], 1)
# print("rank is", tf.rank(x1))
y1 = tf.nn.conv2d(x1, w, strides=[1, 1, 1, 1], padding='SAME')
y2 = slim.conv2d(x1, 64, [5, 5], weights_initializer=tf.ones_initializer, padding='SAME')
 
 
with tf.Session() as sess: 
    sess.run(tf.global_variables_initializer()) 
    y1_value,y2_value,x1_value=sess.run([y1,y2,x1])
    print("shapes are", y1_value.shape, y2_value.shape)
    print(y1_value==y2_value)
    print(y1_value)
    print(y2_value)

最后配上tf.contrib.slim.conv2d的API英文版

def convolution(inputs,
                num_outputs,
                kernel_size,
                stride=1,
                padding='SAME',
                data_format=None,
                rate=1,
                activation_fn=nn.relu,
                normalizer_fn=None,
                normalizer_params=None,
                weights_initializer=initializers.xavier_initializer(),
                weights_regularizer=None,
                biases_initializer=init_ops.zeros_initializer(),
                biases_regularizer=None,
                reuse=None,
                variables_collections=None,
                outputs_collections=None,
                trainable=True,
                scope=None):
  """Adds an N-D convolution followed by an optional batch_norm layer.
  It is required that 1 <= N <= 3.
  `convolution` creates a variable called `weights`, representing the
  convolutional kernel, that is convolved (actually cross-correlated) with the
  `inputs` to produce a `Tensor` of activations. If a `normalizer_fn` is
  provided (such as `batch_norm`), it is then applied. Otherwise, if
  `normalizer_fn` is None and a `biases_initializer` is provided then a `biases`
  variable would be created and added the activations. Finally, if
  `activation_fn` is not `None`, it is applied to the activations as well.
  Performs atrous convolution with input stride/dilation rate equal to `rate`
  if a value > 1 for any dimension of `rate` is specified.  In this case
  `stride` values != 1 are not supported.
  Args:
    inputs: A Tensor of rank N+2 of shape
      `[batch_size] + input_spatial_shape + [in_channels]` if data_format does
      not start with "NC" (default), or
      `[batch_size, in_channels] + input_spatial_shape` if data_format starts
      with "NC".
    num_outputs: Integer, the number of output filters.
    kernel_size: A sequence of N positive integers specifying the spatial
      dimensions of the filters.  Can be a single integer to specify the same
      value for all spatial dimensions.
    stride: A sequence of N positive integers specifying the stride at which to
      compute output.  Can be a single integer to specify the same value for all
      spatial dimensions.  Specifying any `stride` value != 1 is incompatible
      with specifying any `rate` value != 1.
    padding: One of `"VALID"` or `"SAME"`.
    data_format: A string or None.  Specifies whether the channel dimension of
      the `input` and output is the last dimension (default, or if `data_format`
      does not start with "NC"), or the second dimension (if `data_format`
      starts with "NC").  For N=1, the valid values are "NWC" (default) and
      "NCW".  For N=2, the valid values are "NHWC" (default) and "NCHW".
      For N=3, the valid values are "NDHWC" (default) and "NCDHW".
    rate: A sequence of N positive integers specifying the dilation rate to use
      for atrous convolution.  Can be a single integer to specify the same
      value for all spatial dimensions.  Specifying any `rate` value != 1 is
      incompatible with specifying any `stride` value != 1.
    activation_fn: Activation function. The default value is a ReLU function.
      Explicitly set it to None to skip it and maintain a linear activation.
    normalizer_fn: Normalization function to use instead of `biases`. If
      `normalizer_fn` is provided then `biases_initializer` and
      `biases_regularizer` are ignored and `biases` are not created nor added.
      default set to None for no normalizer function
    normalizer_params: Normalization function parameters.
    weights_initializer: An initializer for the weights.
    weights_regularizer: Optional regularizer for the weights.
    biases_initializer: An initializer for the biases. If None skip biases.
    biases_regularizer: Optional regularizer for the biases.
    reuse: Whether or not the layer and its variables should be reused. To be
      able to reuse the layer scope must be given.
    variables_collections: Optional list of collections for all the variables or
      a dictionary containing a different list of collection per variable.
    outputs_collections: Collection to add the outputs.
    trainable: If `True` also add variables to the graph collection
      `GraphKeys.TRAINABLE_VARIABLES` (see tf.Variable).
    scope: Optional scope for `variable_scope`.
  Returns:
    A tensor representing the output of the operation.
  Raises:
    ValueError: If `data_format` is invalid.
    ValueError: Both 'rate' and `stride` are not uniformly 1.