(1)tf.nn.max_pool()函数
解释:
tf.nn.max_pool(value, ksize, strides, padding, data_format='NHWC', name=None) 需要设置的参数主要有四个: 第一个参数value:需要池化的输入,一般池化层接在卷积层后面,所以输入通常是feature map,依然是[batch, height, width, channels]这样的shape 第二个参数ksize:池化窗口的大小,取一个四维向量,一般是[1, height, width, 1],因为我们不想在batch和channels上做池化,所以这两个维度设为了1 第三个参数strides:和卷积类似,窗口在每一个维度上滑动的步长,一般也是[1, stride,stride, 1] 第四个参数padding:和卷积类似,可以取'VALID' 或者'SAME' 返回一个Tensor,类型不变,shape仍然是[batch, height, width, channels]这种形式
示例:
程序: import tensorflow as tf a=tf.constant([ [[1.0,2.0,3.0,4.0], [5.0,6.0,7.0,8.0], [8.0,7.0,6.0,5.0], [4.0,3.0,2.0,1.0]], [[4.0,3.0,2.0,1.0], [8.0,7.0,6.0,5.0], [1.0,2.0,3.0,4.0], [5.0,6.0,7.0,8.0]] ]) a=tf.reshape(a,[1,4,4,2]) pooling=tf.nn.max_pool(a,[1,2,2,1],[1,1,1,1],padding='VALID') with tf.Session() as sess: print("image:") image=sess.run(a) print (image) print("reslut:") result=sess.run(pooling) print (result) 运行结果: image: [[[[ 1. 2.] [ 3. 4.] [ 5. 6.] [ 7. 8.]] [[ 8. 7.] [ 6. 5.] [ 4. 3.] [ 2. 1.]] [[ 4. 3.] [ 2. 1.] [ 8. 7.] [ 6. 5.]] [[ 1. 2.] [ 3. 4.] [ 5. 6.] [ 7. 8.]]]] reslut: [[[[ 8. 7.] [ 6. 6.] [ 7. 8.]] [[ 8. 7.] [ 8. 7.] [ 8. 7.]] [[ 4. 4.] [ 8. 7.] [ 8. 8.]]]]
(2)tf.nn.dropout函数
解释:
tf.nn.dropout(x, keep_prob, noise_shape=None, seed=None, name=None) 此函数是为了防止在训练中过拟合的操作,将训练输出按一定规则进行变换 参数: x:输入 keep_prob:保留比例。 取值 (0,1] 。每一个参数都将按这个比例随机变更 noise_shape:干扰形状。 此字段默认是None,表示第一个元素的操作都是独立,但是也不一定。比例:数据的形状是shape(x)=[k, l, m, n],而noise_shape=[k, 1, 1, n],则第1和4列是独立保留或删除,第2和3列是要么全部保留,要么全部删除。 seed:整形变量,随机数种子。 name:名字,没啥用 返回:Tnesor
(3)tf.nn.local_response_normalization函数
公式说明
local response normalization最早是由Krizhevsky和Hinton在关于ImageNet的论文里面使用的一种数据标准化方法,即使现在,也依然会有不少CNN网络会使用到这种正则手段,现在记录一下lrn方法的计算流程以及tensorflow的实现,方便后面查阅
以上是这种归一手段的公式,其中a的上标指该层的第几个feature map,a的下标x,y表示feature map的像素位置,N指feature map的总数量,公式里的其它参数都是超参,需要自己指定的。
这种方法是受到神经科学的启发,激活的神经元会抑制其邻近神经元的活动(侧抑制现象),至于为什么使用这种正则手段,以及它为什么有效,查阅了很多文献似乎也没有详细的解释,可能是由于后来提出的batch normalization手段太过火热,渐渐的就把local response normalization掩盖了吧
解释:
tf.nn.local_response_normalization(input, depth_radius=5, bias=1, alpha=1, beta=0.5, name=None) 除去name参数用以指定该操作的name,与方法有关的一共五个参数: 第一个参数input:这个输入就是feature map了,既然是feature map,那么它就具有[batch, height, width, channels]这样的shape 第二个参数depth_radius:这个值需要自己指定,就是上述公式中的n/2 第三个参数bias:上述公式中的k 第四个参数alpha:上述公式中的α 第五个参数beta:上述公式中的β
程序:
import tensorflow as tf a = tf.constant([ [[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0], [8.0, 7.0, 6.0, 5.0], [4.0, 3.0, 2.0, 1.0]], [[4.0, 3.0, 2.0, 1.0], [8.0, 7.0, 6.0, 5.0], [1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]] ]) #reshape a,get the feature map [batch:1 height:2 2 channels:8] a = tf.reshape(a, [1, 2, 2, 8]) normal_a=tf.nn.local_response_normalization(a,2,0,1,1) with tf.Session() as sess: print("feature map:") image = sess.run(a) print (image) print("normalized feature map:") normal = sess.run(normal_a) print (normal)
输出结果:
feature map: [[[[ 1. 2. 3. 4. 5. 6. 7. 8.] [ 8. 7. 6. 5. 4. 3. 2. 1.]] [[ 4. 3. 2. 1. 8. 7. 6. 5.] [ 1. 2. 3. 4. 5. 6. 7. 8.]]]] normalized feature map: [[[[ 0.07142857 0.06666667 0.05454545 0.04444445 0.03703704 0.03157895 0.04022989 0.05369128] [ 0.05369128 0.04022989 0.03157895 0.03703704 0.04444445 0.05454545 0.06666667 0.07142857]] [[ 0.13793103 0.10000001 0.0212766 0.00787402 0.05194805 0.04 0.03448276 0.04545454] [ 0.07142857 0.06666667 0.05454545 0.04444445 0.03703704 0.03157895 0.04022989 0.05369128]]]]
(4)tf.get_variable函数
函数定义:
get_variable( name, shape=None, dtype=None, initializer=None, regularizer=None, trainable=True, collections=None, caching_device=None, partitioner=None, validate_shape=True, use_resource=None, custom_getter=None )
其中参数分别为:
参数: name:新变量或现有变量的名称。 shape:新变量或现有变量的形状。 dtype:新变量或现有变量的类型(默认为 DT_FLOAT)。 initializer:创建变量的初始化器。 regularizer:一个函数(张量 - >张量或无);将其应用于新创建的变量的结果将被添加到集合 tf.GraphKeys.REGULARIZATION_LOSSES 中,并可用于正则化。 trainable:如果为 True,还将变量添加到图形集合:GraphKeys.TRAINABLE_VARIABLES。 collections:要将变量添加到其中的图形集合键的列表。默认为 [GraphKeys.LOCAL_VARIABLES]。 caching_device:可选的设备字符串或函数,描述变量应该被缓存以读取的位置。默认为变量的设备,如果不是 None,则在其他设备上进行缓存。典型的用法的在使用该变量的操作所在的设备上进行缓存,通过 Switch 和其他条件语句来复制重复数据删除。 partitioner:(可选)可调用性,它接受要创建的变量的完全定义的 TensorShape 和 dtype,并且返回每个坐标轴的分区列表(当前只能对一个坐标轴进行分区)。 validate_shape:如果为假,则允许使用未知形状的值初始化变量。如果为真,则默认情况下,initial_value 的形状必须是已知的。 use_resource:如果为假,则创建一个常规变量。如果为真,则创建一个实验性的 ResourceVariable,而不是具有明确定义的语义。默认为假(稍后将更改为真)。 custom_getter:可调用的,将第一个参数作为真正的 getter,并允许覆盖内部的 get_variable 方法。custom_getter 的签名应该符合这种方法,但最经得起未来考验的版本将允许更改:def custom_getter(getter, *args, **kwargs)。还允许直接访问所有 get_variable 参数:def custom_getter(getter, name, *args, **kwargs)。创建具有修改的名称的变量的简单标识自定义 getter 是:python def custom_getter(getter, name, *args, **kwargs): return getter(name + '_suffix', *args, **kwargs)
使用例子:
w = tf.get_variable("w", shape = [inputD, outputD], dtype = "float") b = tf.get_variable("b", [outputD], dtype = "float")
(5)tf.variable_scope函数
函数原理
用于定义创建变量(层)的操作的上下文管理器。
此上下文管理器验证(可选)values是否来自同一图形,确保图形是默认的图形,并推送名称范围和变量范围。
如果name_or_scope不是None,则使用as is。如果scope是None,则使用default_name。在这种情况下,如果以前在同一范围内使用过相同的名称,则通过添加_N来使其具有唯一性。
变量范围允许您创建新变量并共享已创建的变量,同时提供检查以防止意外创建或共享。在本文中我们提供了几个基本示例。
如何创建一个新变量:
with tf.variable_scope("foo"): with tf.variable_scope("bar"): v = tf.get_variable("v", [1]) assert v.name == "foo/bar/v:0"
(6)tf.nn.relu函数
解释
这个函数的作用是计算激活函数relu,即max(features, 0)。即将矩阵中每行的非最大值置0。
类似的还有tf.sigmoid , tf.tanh
函数定义:
>>> help(tf.nn.relu) Help on function relu in module tensorflow.python.ops.gen_nn_ops: relu(features, name=None) Computes rectified linear: `max(features, 0)`. Args: features: A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. name: A name for the operation (optional). Returns: A `Tensor`. Has the same type as `features`.
程序示例:
#!/usr/bin/env python # -*- coding: utf-8 -*- import tensorflow as tf a = tf.constant([-1.0, 2.0]) with tf.Session() as sess: b = tf.nn.relu(a) print sess.run(b)
运行结果:
[0. 2.]
(7)tf.nn.bias_add函数
函数定义:
tf.nn.bias_add(value, bias, data_format=None, name=None) 对value加一偏置量 此函数为tf.add的特殊情况,bias仅为一维, 函数通过广播机制进行与value求和, 数据格式可以与value不同,返回为与value相同格式
官方释义:
>>> help(tf.nn.bias_add) Help on function bias_add in module tensorflow.python.ops.nn_ops: bias_add(value, bias, data_format=None, name=None) Adds `bias` to `value`. This is (mostly) a special case of `tf.add` where `bias` is restricted to 1-D. Broadcasting is supported, so `value` may have any number of dimensions. Unlike `tf.add`, the type of `bias` is allowed to differ from `value` in the case where both types are quantized. Args: value: A `Tensor` with type `float`, `double`, `int64`, `int32`, `uint8`, `int16`, `int8`, `complex64`, or `complex128`. bias: A 1-D `Tensor` with size matching the last dimension of `value`. Must be the same type as `value` unless `value` is a quantized type, in which case a different quantized type may be used. data_format: A string. 'NHWC' and 'NCHW' are supported. name: A name for the operation (optional). Returns: A `Tensor` with the same type as `value`.
使用示例:
out = tf.nn.bias_add(mergeFeatureMap, b)
(8)tf.nn.xw_plus_b函数
官方解释:
>>> help(tf.nn.xw_plus_b) Help on function xw_plus_b in module tensorflow.python.ops.nn_ops: xw_plus_b(x, weights, biases, name=None) Computes matmul(x, weights) + biases. Args: x: a 2D tensor. Dimensions typically: batch, in_units weights: a 2D tensor. Dimensions typically: in_units, out_units biases: a 1D tensor. Dimensions: out_units name: A name for the operation (optional). If not specified "xw_plus_b" is used. Returns: A 2-D Tensor computing matmul(x, weights) + biases. Dimensions typically: batch, out_units.
使用示例:
out = tf.nn.xw_plus_b(x, w, b, name = scope.name)
解释:
xw_plus_b(x, weights, biases, name=None)相当于matmul(x, weights) + biases.
(9)tf.nn.conv2d函数
官方解释:
>>> help(tf.nn.conv2d) Help on function conv2d in module tensorflow.python.ops.gen_nn_ops: conv2d(input, filter, 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]`. Args: input: A `Tensor`. Must be one of the following types: `half`, `bfloat16`, `float32`. A 4-D tensor. The dimension order is interpreted according to the value of `data_format`, see below for details. filter: A `Tensor`. Must have the same type as `input`. A 4-D tensor of shape `[filter_height, filter_width, in_channels, out_channels]` strides: A list of `ints`. 1-D tensor of length 4. The stride of the sliding window for each dimension of `input`. The dimension order is determined by the value of `data_format`, see below for details. padding: A `string` from: `"SAME", "VALID"`. The type of padding algorithm to use. use_cudnn_on_gpu: An optional `bool`. Defaults to `True`. data_format: An optional `string` from: `"NHWC", "NCHW"`. Defaults to `"NHWC"`. Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, height, width, channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, channels, height, width]. dilations: An optional list of `ints`. Defaults to `[1, 1, 1, 1]`. 1-D tensor of length 4. The dilation factor for each dimension of `input`. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of `data_format`, see above for details. Dilations in the batch and depth dimensions must be 1. name: A name for the operation (optional). Returns: A `Tensor`. Has the same type as `input`.
函数释义:
此函数的作用是在给定四维输入(input)和权重W(filter)的情况下计算二维卷积。 参数解释: input: 一个Tensor,每个元素的格式必须为float32或float64. input的形状:[batch,in_height,in_width,in_channels], batch为训练过程中每迭代一次迭代的照片数。 in_height,in_width分别为图片的高和宽 in_channels为图片的道。 filter: 一个Tensor,每个元素的类型和input类型一致。 filter的形状:[filter_height,filter_width,in_channels,out_channels] 分别为权重的height,width,输入的channels和输出的channels stride: 长度为4的list,元素类型为int。表示每一维度滑动的步长。 需要注意的是,strides[0]=strides[3]=1. padding: 可选参数为"Same","VALID" 边距,一般设为0,即padding='SAME' use_cudnn_on_gpu: bool类型,有True和False两种选择。 name: 此操作的名字
函数执行以下操作: 1.将参数filter变为一个二维矩阵,形状为:[filter_height*filter_width*in_channels,output_channels] 2.将输入(input)转化为一个具有如下形状的Tensor,形状为:[batch,out_height,out_width,filter_height * filter_width * in_channels] 3.将filter矩阵和步骤2得到的矩阵相乘。
函数的返回值:
元素类型和input相同。
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]
编程示例:
kernel = tf.Variable(tf.truncated_normal([3,3,384,256], dtype=tf.float32, stddev=1e-1), name='weights') conv = tf.nn.conv2d(conv3, kernel, [1,1,1,1],padding='SAME')
(10)tf.constant函数
官方解释:
>>> help(tf.constant) Help on function constant in module tensorflow.python.framework.constant_op: constant(value, dtype=None, shape=None, name='Const', verify_shape=False) Creates a constant tensor. The resulting tensor is populated with values of type `dtype`, as specified by arguments `value` and (optionally) `shape` (see examples below). The argument `value` can be a constant value, or a list of values of type `dtype`. If `value` is a list, then the length of the list must be less than or equal to the number of elements implied by the `shape` argument (if specified). In the case where the list length is less than the number of elements specified by `shape`, the last element in the list will be used to fill the remaining entries. The argument `shape` is optional. If present, it specifies the dimensions of the resulting tensor. If not present, the shape of `value` is used. If the argument `dtype` is not specified, then the type is inferred from the type of `value`. For example: ```python # Constant 1-D Tensor populated with value list. tensor = tf.constant([1, 2, 3, 4, 5, 6, 7]) => [1 2 3 4 5 6 7] # Constant 2-D tensor populated with scalar value -1. tensor = tf.constant(-1.0, shape=[2, 3]) => [[-1. -1. -1.] [-1. -1. -1.]] ``` Args: value: A constant value (or list) of output type `dtype`. dtype: The type of the elements of the resulting tensor. shape: Optional dimensions of resulting tensor. name: Optional name for the tensor. verify_shape: Boolean that enables verification of a shape of values. Returns: A Constant Tensor. Raises: TypeError: if shape is incorrectly specified or unsupported.
程序示例:
https://blog.csdn.net/qq_26591517/article/details/80198471