在查看代码的时候,看到有代码用到卷积层是tf.nn.conv2d,但是也有的使用的卷积层是tf.contrib.slim.conv2d,这两个函数调用的卷积层是否一致,在查看了API的文档,以及slim.conv2d的源码后,做如下总结:
tf.nn.conv2d函数
定义如下:
conv2d(
input,
filter,
strides,
padding,
use_cudnn_on_gpu=None,
data_format=None,
name=None
)
- input:
指需要做卷积的输入图像,它要求是一个Tensor,具有[batch_size, in_height, in_width, in_channels]这样的shape,具体含义是[训练时一个batch的图片数量, 图片高度, 图片宽度, 图像通道数],注意这是一个4维的Tensor,要求数据类型为float32和float64其中之一。
- filter
用于指定CNN中的卷积核,它要求是一个Tensor,具有[filter_height, filter_width, in_channels, out_channels]这样的shape,具体含义是[卷积核的高度,卷积核的宽度,图像通道数,卷积核个数],要求类型与参数input相同,有一个地方需要注意,第三维in_channels,就是参数input的第四维,这里是维度一致,不是数值一致
- strides
为卷积时在图像每一维的步长,这是一个一维的向量,长度为4,对应的是在input的4个维度上的步长
- padding
string类型的变量,只能是"SAME","VALID"其中之一,这个值决定了不同的卷积方式,SAME代表卷积核可以停留图像边缘,VALID表示不能
- use_cudnn_on_gpu
指定是否使用cudnn加速,默认为true
- data_format
是用于指定输入的input的格式,默认为NHWC格式
结果返回一个Tensor,这个输出,就是我们常说的feature map
tf.contrib.slim.conv2d函数
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
指需要做卷积的输入图像
- num_outputs
指定卷积核的个数(就是filter的个数)
- kernel_size
指定卷积核的维度(卷积核的宽度,卷积核的高度)
- stride
为卷积时在图像每一维的步长
- padding
为padding的方式选择,VALID或者SAME
- data_format
是用于指定输入的input的格式
- rate
而且tf.nn.conv2d中没有,对于使用atrous convolution的膨胀率
- activation_fn
用于激活函数的指定,默认的为ReLU函数
- normalizer_fn
用于指定正则化函数
- normalizer_params
用于指定正则化函数的参数
- weights_initializer
用于指定权重的初始化程序
- weights_regularizer
为权重可选的正则化程序
- biases_initializer
用于指定biase的初始化程序
- biases_regularizer: biases
可选的正则化程序
- reuse
指定是否共享层或者和变量
- variable_collections
指定所有变量的集合列表或者字典
- outputs_collections
指定输出被添加的集合
- trainable
卷积层的参数是否可被训练
- scope
共享变量所指的variable_scope
在上述的API中,可以看出去除掉初始化的部分,那么两者并没有什么不同,只是tf.contrib.slim.conv2d提供了更多可以指定的初始化的部分,而对于tf.nn.conv2d而言,其指定filter的方式相比较tf.contrib.slim.conv2d来说,更加的复杂。去除掉少用的初始化部分,其实两者的API可以简化如下:
tf.contrib.slim.conv2d (inputs,
num_outputs,[卷积核个数]
kernel_size,[卷积核的高度,卷积核的宽度]
stride=1,
padding='SAME',
)
tf.nn.conv2d(
input,(与上述一致)
filter,([卷积核的高度,卷积核的宽度,图像通道数,卷积核个数])
strides,
padding,
)
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.