Tensotflow1.0入门(四)-tensorflow的卷积函数

水深无声 2022-02-24 09:18 274阅读 0赞

[Tensotflow1.0入门(一)-tensorflow的设计理念和基本概念][Tensotflow1.0_-tensorflow]  
[Tensotflow1.0入门(二)-tensorflow的各种操作][Tensotflow1.0_-tensorflow 1]  
[Tensotflow1.0入门(三)-tensorflow的小例子][Tensotflow1.0_-tensorflow 2]  
[Tensotflow1.0入门(四)-tensorflow的卷积函数][Tensotflow1.0_-tensorflow 3]  
[Tensotflow1.0入门(五)-tensorflow的池化函数][Tensotflow1.0_-tensorflow 4]  
[Tensotflow1.0入门(六)-tensorflow的激活函数][Tensotflow1.0_-tensorflow 5]

**卷积函数的定义在tensorflow/python/ops/nn.py，但其实这个nn.py是由很多别的文件中的类和方法组成的，其中激活函数也包含在内了，而卷积函数的定义主要在nn\_impl.py和nn\_ops.py**

tf.nn.convolution(input, filter, padding, strides, dilation\_rate, name, data\_format)  
tf.nn.conv2d(input, filter, strides, padding, use\_cudnn\_on\_gpu, data\_format, name)  
tf.nn.depthwise\_conv2d(input, filter, strides, padding, rate, name)  
tf.nn.separable\_conv2d(input, depthwise\_filter, pointwise\_filter, strides, padding, rate, name)  
tf.nn.atrous\_conv2d(value, filters, rate, padding, name)  
tf.nn.conv2d\_transpose(value, filter, output\_shape, strides, padding, data\_format, name)  
tf.nn.conv1d(value, filters, stride, padding, use\_cudnn\_on\_gpu, data\_format, name)  
tf.nn.conv3d(input, filter, strides, padding, name)  
tf.nn.conv3d\_transpose(value, filter, output\_shape, strides, padding, name)

\#参数  
input: Tensor,数据类型必须是float32或者64  
filter: Tensor，数据类型要与input相同  
strides: 一个长度为4的一维整数类型数组  
padding: 字符串，“SAME”|“VALID”,SAME输入数据维度和输出维度相同  
name: 操作的名字

import tensorflow as tf
    import numpy as np
    
    # (batch_size,w,h,channels_last)=(32,9,9,3)
    input_data = tf.Variable(np.random.rand(32,9,9,3),dtype=np.float32)
    # (w,h,channels_last,filter_nums)=(32,9,9,3)
    filter_data = tf.Variable(np.random.rand(2,2,3,5),dtype=np.float32)
    # y = tf.nn.convolution(input_data, filter_data, strides=[1,1], padding="SAME")
    y = tf.nn.conv2d(input_data, filter_data, strides=[1,1,1,1], padding="SAME")
    init = tf.global_variables_initializer()
    sess = tf.Session()
    sess.run(init)
    print(sess.run(y).shape)

参考:《TensorFlow 技术解析与实战》

[Tensotflow1.0_-tensorflow]: https://blog.csdn.net/u011311291/article/details/88959590
[Tensotflow1.0_-tensorflow 1]: https://blog.csdn.net/u011311291/article/details/88959599
[Tensotflow1.0_-tensorflow 2]: https://blog.csdn.net/u011311291/article/details/89057972
[Tensotflow1.0_-tensorflow 3]: https://blog.csdn.net/u011311291/article/details/89000644
[Tensotflow1.0_-tensorflow 4]: https://blog.csdn.net/u011311291/article/details/89003525
[Tensotflow1.0_-tensorflow 5]: https://blog.csdn.net/u011311291/article/details/89000263