tensorflow编程: Layers (contrib)

JNingWei

发布于 2018-09-28 07:39:11

81000

代码可运行

文章被收录于专栏：JNing的专栏JNing的专栏

运行总次数：0

代码可运行

Higher level ops for building neural network layers

tf.contrib.layers.batch_norm

添加一个 Batch Normalization 层 。

tf.contrib.layers.batch_norm (inputs, decay=0.999, updates_collections=tf.GraphKeys.UPDATE_OPS, is_training=True, data_format=DATA_FORMAT_NHWC)

可用作conv2d和fully_connected的归一化函数。

tf.nn.conv2d_transpose

conv2d 的转置

tf.conv2d_transpose (value, filter, output_shape, strides, padding=’SAME’, data_format=’NHWC’, name=None)

# -*- coding: utf-8 -*-

import tensorflow as tf


def func(in_put, in_channel, out_channel):

    weights = tf.get_variable(name="weights", shape=[2, 2, in_channel, out_channel],
                              initializer=tf.contrib.layers.xavier_initializer_conv2d())
    convolution = tf.nn.conv2d(input=in_put, filter=weights, strides=[1, 1, 1, 1], padding='VALID')
    conv_shape = convolution.get_shape().as_list()
    deconv_shape = [conv_shape[0], conv_shape[1]*2, conv_shape[2]*2, conv_shape[3]]
    deconvolution = tf.nn.conv2d_transpose(value=convolution, filter=weights, output_shape=deconv_shape, strides=[1, 2, 2, 1], padding='VALID')
    return in_put, convolution, deconvolution


def main():

    with tf.Graph().as_default():
        input_x = tf.placeholder(dtype=tf.float32, shape=[1, 4, 4, 1])
        in_put, convolution, deconvolution = func(input_x, 1, 1)

        with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            import numpy as np
            _in_put, _convolution, _deconvolution = sess.run([in_put, convolution, deconvolution], feed_dict={input_x:np.random.uniform(low=0, high=255, size=[1, 4, 4, 1])})
            print '\nin_put:'
            print in_put
            # print _in_put
            print '\nconvolution:'
            print convolution
            # print _convolution
            print '\ndeconvolution:'
            print deconvolution
            # print _deconvolution

if __name__ == "__main__":
    main()

2017-09-29 09:51:41.472842: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)

in_put:
Tensor("Placeholder:0", shape=(1, 4, 4, 1), dtype=float32)

convolution:
Tensor("Conv2D:0", shape=(1, 3, 3, 1), dtype=float32)

deconvolution:
Tensor("conv2d_transpose:0", shape=(1, 6, 6, 1), dtype=float32)

Process finished with exit code 0

tf.nn.dropout

tf.nn.dropout (x, keep_prob, noise_shape=None, seed=None, name=None)

# coding=utf-8

import tensorflow as tf

def main():

    with tf.Graph().as_default():
        import numpy as np
        input_x = np.random.uniform(0, 255, [3, 3])
        print input_x

        drop = [0, 0, 0]
        for i, keep_prob in enumerate([0.1, 0.5, 1.0]):
            drop[i] = tf.nn.dropout(x=input_x, keep_prob=keep_prob)
        with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            for drop_i in drop:
                _drop_i = sess.run(drop_i)
                print '\n----------\n'
                print _drop_i

if __name__ == "__main__":
    main()

# 初始输入
[[  16.46278229  253.27597997  246.33614039]
 [ 130.45261984  227.85971767  142.72621045]
 [ 173.23025953  165.99906514  180.13238617]]

2017-09-29 11:02:29.146976: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)

----------
# keep_prob = 0.1
[[    0.            0.            0.       ]
 [    0.            0.            0.       ]
 [    0.            0.         1801.3238617]]

----------
# keep_prob = 0.5
[[  32.92556457  506.55195994    0.        ]
 [ 260.90523969  455.71943533    0.        ]
 [ 346.46051906    0.          360.26477234]]

----------
# keep_prob = 1.0
[[  16.46278229  253.27597997  246.33614039]
 [ 130.45261984  227.85971767  142.72621045]
 [ 173.23025953  165.99906514  180.13238617]]

tf.contrib.layers.fully_connected

tf.contrib.layers.fully_connected (inputs, num_outputs, activation_fn=tf.nn.relu)

其中默认进行了 convolution 和 activation 。
convolution 中，只对输入的最后一维求平均，且阶数不变。即 ‘weights:0’.shape=[inputs.shape[-1], num_outputs]）。
‘weights:0’.shape 永远是二维的。
num_outputs 是 ‘weights:0’ 第二维（即第-1维）的参数值；经过fn计算后，也变成了结果输出的tensor 的最后一维（即第-1维）的参数值。
如果设置 activation_fn=None，则输出结果不经过激活，依然可能包含负数值。

# coding=utf-8

import tensorflow as tf
from tensorflow.contrib.layers import fully_connected

def main():

    with tf.Graph().as_default():
        import numpy as np
        input_x = np.random.uniform(0, 10, [3, 3])
        print input_x
        fn = fully_connected(inputs=input_x, num_outputs=1)
        with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            _fn = sess.run(fn)
            print _fn
            print '\n----------\n'
            for (x, y) in zip(tf.global_variables(), sess.run(tf.global_variables())):
                print '\n', x, '\n', y

if __name__ == "__main__":
    main()

# 原始输入矩阵
[[ 7.73305319  0.2780667   7.27101124]
 [ 0.84666041  0.92980727  6.83676724]
 [ 1.02844109  5.51824496  1.78840816]]

2017-09-29 11:33:02.500942: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)

# fn后输出的结果tensor
[[ 2.32549239]
 [ 1.69284669]
 [ 0.        ]]

----------

<tf.Variable 'fully_connected/weights:0' shape=(3, 1) dtype=float64_ref> 
[[-0.01048241]
 [-0.83954232]
 [ 0.36308597]]

<tf.Variable 'fully_connected/biases:0' shape=(1,) dtype=float64_ref> 
[ 0.]

Process finished with exit code 0

# coding=utf-8

import tensorflow as tf
from tensorflow.contrib.layers import fully_connected

def main():

    with tf.Graph().as_default():
        import numpy as np
        input_x = np.random.uniform(0, 10, [2, 4, 4, 3])
        print np.shape(input_x)

        fn = fully_connected(inputs=input_x, num_outputs=1)
        with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            _fn = sess.run(fn)
            print np.shape(_fn)
            print '\n----------\n'
            for i in tf.global_variables():
                print '\n', i

if __name__ == "__main__":
    main()

(2, 4, 4, 3)

2017-09-29 11:46:17.248114: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)
# convolution 中，只对输入的最后一维求平均，且阶数不变。即 'weights:0'.shape=[inputs.shape[-1], num_outputs]）。
(2, 4, 4, 1)

----------

<tf.Variable 'fully_connected/weights:0' shape=(3, 1) dtype=float64_ref>

<tf.Variable 'fully_connected/biases:0' shape=(1,) dtype=float64_ref>

tf.nn.relu

max(features, 0)

tf.nn.relu(features, name=None)

tf.nn.relu6

min(max(features, 0), 6)。即对 tf.nn.relu 的优化，防止 relu过后某些 极端值 依然 大于6

tf.nn.relu6(features, name=None)

tf.nn.softmax

计算公式： softmax = exp(logits) / reduce_sum(exp(logits), dim)

tf.nn.softmax (logits, dim=-1, name=None)

# coding=utf-8

import tensorflow as tf
import numpy as np
input_x = tf.constant(np.random.uniform(0, 5, [2, 3]))
softmax = tf.nn.softmax(logits=input_x)

# 自己写的softmax接口
def my_softmax(logits, dim=-1):
    my_softmax = tf.div(tf.exp(logits), tf.reduce_sum(tf.exp(logits), dim, keep_dims=True))
    return my_softmax

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    my_softmax = my_softmax(logits=input_x)
    _input_x, _softmax, _my_softmax = sess.run([input_x, softmax, my_softmax])
    print 'input:', np.shape(input_x), input_x, '\n', _input_x
    print '\n----------\n'
    print 'softmax:', np.shape(_softmax), softmax, '\n', _softmax
    print '\n----------\n'
    print 'my_softmax:', np.shape(_my_softmax), my_softmax, '\n', _my_softmax
    print '\n----------\n'
    for i in tf.global_variables():
        print '\n', i

# softmax输入类型为tensor型
input: (2, 3) Tensor("Const:0", shape=(2, 3), dtype=float64) 
[[ 3.88517858  3.69402461  3.07837121]
 [ 1.27162028  2.12622856  4.34646188]]

----------
# softmax后，shape保持不变，返回tensor型
softmax: (2, 3) Tensor("Softmax:0", shape=(2, 3), dtype=float64) 
[[ 0.44008545  0.36351295  0.1964016 ]
 [ 0.04000495  0.09402978  0.86596527]]

----------
# 根据计算公式：softmax = exp(logits) / reduce_sum(exp(logits), dim) 得到了相同的接口输出
my_softmax: (2, 3) Tensor("div:0", shape=(2, 3), dtype=float64) 
[[ 0.44008545  0.36351295  0.1964016 ]
 [ 0.04000495  0.09402978  0.86596527]]

----------
# 内存中无参数保存

Process finished with exit code 0

Regularizers

tf.contrib.layers.l1_regularizer

tf.contrib.layers.l1_regularizer (scale, scope=None)

tf.contrib.layers.l2_regularizer

tf.contrib.layers.l2_regularizer (scale, scope=None)

Initializers

tf.contrib.layers.xavier_initializer

执行“Xavier”初始化的初始化程序。

tf.contrib.layers.xavier_initializer (uniform=True, seed=None, dtype=tf.float32)

# coding=utf-8

import tensorflow as tf

xavier = tf.get_variable(name="weights",
                         shape=[2, 2],
                         initializer=tf.contrib.layers.xavier_initializer())
constant = tf.get_variable(name='biases',
                         shape=[2],
                         initializer=tf.constant_initializer())

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    _xavier, _constant = sess.run([xavier, constant])
    print '\n\nxavier:'
    print xavier
    print _xavier
    print '\n\nconstant:'
    print constant
    print _constant

xavier:
<tf.Variable 'weights:0' shape=(2, 2) dtype=float32_ref>
[[ 1.20015538  0.34742999]
 [ 0.39075291  0.60076308]]


constant:
<tf.Variable 'biases:0' shape=(2,) dtype=float32_ref>
[ 0.  0.]

import tensorflow as tf

print '\n\ntf.contrib.layers.xavier_initializer_conv2d() :\n', tf.contrib.layers.xavier_initializer_conv2d()
print '\n\ntf.constant_initializer() :\n', tf.constant_initializer()
print '\n\ntf.global_variables_initializer() :\n', tf.global_variables_initializer()

tf.contrib.layers.xavier_initializer_conv2d() :
<function _initializer at 0x7fe5133da578>


tf.constant_initializer() :
<tensorflow.python.ops.init_ops.Constant object at 0x7fe528bbdfd0>


tf.global_variables_initializer() :
name: "init"
op: "NoOp"