tf.nn.conv2d和tf.contrib.slim.conv2d的区别

转自：http://blog.sina.com.cn/s/blog_6ca0f5eb0102wsuu.html

文中摘要：

“

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,

)

可以说两者是几乎相同的，运行下列代码也可知这两者一致

”

详细说明：

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：

首先是常见使用的tf.nn.conv2d的函数，其定义如下：

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。这里out_channels指定的是卷积核的个数，而in_channels说明卷积核的维度与图像的维度一致，在做卷积的时候，单个卷积核在不同维度上对应的卷积图片，然后将in_channels个通道上的结果相加，加上bias来得到单个卷积核卷积图片的结果。

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是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，更详细的描述可以参考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

而对于tf.contrib.slim.conv2d，其函数定义如下：

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同样是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用于指定卷积核的维度（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这个参数不是太理解，而且tf.nn.conv2d中也没有，对于使用atrous convolution的膨胀率（不是太懂这个 atrous convolution）

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

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]

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,

)

可以说两者是几乎相同的，运行下列代码也可知这两者一致

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,

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.

tf.nn.conv2d和tf.contrib.slim.conv2d的区别相关推荐

TensorFlow学习——tf.nn.conv2d和tf.contrib.slim.conv2d的区别
在查看代码的时候,看到有代码用到卷积层是tf.nn.conv2d,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. ...
tf.nn.softmax_cross_entropy_with_logits 和 tf.contrib.legacy_seq2seq.sequence_loss_by_example 的联系与区别
文章目录 0.函数介绍 1.区别联系 1.1 tf.nn.softmax_cross_entropy_with_logits 1.2 tf.nn.sparse_softmax_cross_entrop ...
【TensorFlow】TensorFlow函数精讲之tf.nn.max_pool()和tf.nn.avg_pool()
tf.nn.max_pool()和tf.nn.avg_pool()是TensorFlow中实现最大池化和平均池化的函数,在卷积神经网络中比较核心的方法. 有些和卷积很相似,可以参考TensorFlow ...
TensorFlow基础篇（六）——tf.nn.max_pool()和tf.nn.avg_pool()
tf.nn.max_pool()和tf.nn.avg_pool()是TensorFlow中实现最大池化和平均池化的函数,在卷积神经网络中比较核心的方法. 有些和卷积很相似,可以参考TensorFlow ...
tf.nn.dropout和tf.keras.layers.Dropout的区别（TensorFlow2.3）与实验
这里写目录标题场景:dropout和Dropout区别问题描述: 结论: 深层次原因:dropout是底层API,Dropout是高层API 场景:dropout和Dropout区别全网搜索tf ...
TensorFlow 辨异 —— tf.add(a, b) 与 a+b（tf.assign 与 =）、tf.nn.bias_add 与 tf.add
1. tf.add(a, b) 与 a+b 在神经网络前向传播的过程中,经常可见如下两种形式的代码: tf.add(tf.matmul(x, w), b) tf.matmul(x, w) + b 简而 ...
tensorflow 的 Batch Normalization 实现（tf.nn.moments、tf.nn.batch_normalization）
tensorflow 在实现 Batch Normalization(各个网络层输出的归一化)时,主要用到以下两个 api: tf.nn.moments(x, axes, name=None, kee ...
tf.nn.sparse_softmax_cross_entropy_with_logits()与tf.nn.softmax_cross_entropy_with_logits的差别
这两个函数的用法类似 sparse_softmax_cross_entropy_with_logits(_sentinel=None, labels=None, logits=None, name=N ...
深度学习-函数-tf.nn.embedding_lookup 与tf.keras.layers.Embedding
embedding函数用法 1. one_hot编码 1.1. 简单对比 1.2.优势分析: 1.3. 缺点分析: 1.4. 延伸思考 2. embedding的用途 2.1 embedding有两个 ...

tf.nn.conv2d和tf.contrib.slim.conv2d的区别

tf.nn.conv2d和tf.contrib.slim.conv2d的区别相关推荐

最新文章

热门文章