一维卷积filter_tensorflow中一维卷积conv1d处理语言序列的一点记录
工作中用卷积方法进行自然语言处理(NLP)相关任务，用到了tensorflow中的一些函数及方法：
tf.nn.conv1d
tf.layters.conv1d
用cov2d实现cov1d
两种池化操作
不同核尺寸卷积操作
下面分别介绍
tf.nn.conv1d：
函数形式： tf.nn.conv1d(value, filters, stride, padding, use_cudnn_on_gpu=None, data_format=None, name=None):
程序举例：
import tensorflow as tf
import numpy as np
sess = tf.InteractiveSession()
# --------------- tf.nn.conv1d -------------------
inputs=tf.ones((64,10,3)) # [batch, n_sqs, embedsize]
w=tf.constant(1,tf.float32,(5,3,32)) # [w_high, embedsize, n_filers]
conv1 = tf.nn.conv1d(inputs,w,stride=2 ,padding='SAME') # conv1=[batch, round(n_sqs/stride), n_filers],stride是步长。
tf.global_variables_initializer().run()
out = sess.run(conv1)
print(out)
tf.layters.conv1d：
函数形式：tf.layters.conv1d(inputs, filters, kernel_size, strides=1, padding='valid', data_format='channels_last', dilation_rate=1, activation=None, use_bias=True，...)
程序举例：
import tensorflow as tf
import numpy as np
sess = tf.InteractiveSession()
# --------------- tf.layters.conv1d -------------------
inputs=tf.ones((64,10,3)) # [batch, n_sqs, embedsize]
num_filters=32
kernel_size =5
conv2 = tf.layers.conv1d(inputs, num_filters, kernel_size,strides=2, padding='valid',name='conv2') # shape = (batchsize, round(n_sqs/strides),num_filters)
tf.global_variables_initializer().run()
out = sess.run(conv2)
print(out)
二维卷积实现一维卷积:
import tensorflow as tf
sess = tf.InteractiveSession()
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def max_pool_1x2(x):
return tf.nn.avg_pool(x, ksize=[1,1,2,1], strides=[1,1,2,1], padding='SAME')
'''
ksize = [x, pool_height, pool_width, x]
strides = [x, pool_height, pool_width, x]
'''
x = tf.Variable([[1,2,3,4]], dtype=tf.float32)
x = tf.reshape(x, [1,1,4,1]) #这一步必不可少，否则会报错说维度不一致；
'''
[batch, in_height, in_width, in_channels] = [1,1,4,1]
'''
W_conv1 = tf.Variable([1,1,1],dtype=tf.float32) # 权重值
W_conv1 = tf.reshape(W_conv1, [1,3,1,1]) # 这一步同样必不可少
'''
[filter_height, filter_width, in_channels, out_channels]
'''
h_conv1 = conv2d(x, W_conv1) # 结果：[4,8,12,11]
h_pool1 = max_pool_1x2(h_conv1)
tf.global_variables_initializer().run()
print(sess.run(h_conv1)) # 结果array([6,11.5])x
两种池化操作：
# 1:stride max pooling
convs = tf.expand_dims(conv, axis=-1) # shape=[?,596,256,1]
smp = tf.nn.max_pool(value=convs, ksize=[1, 3, self.config.num_filters, 1], strides=[1, 3, 1, 1],
padding='SAME') # shape=[?,299,256,1]
smp = tf.squeeze(smp, -1) # shape=[?,299,256]
smp = tf.reshape(smp, shape=(-1, 199 * self.config.num_filters))
# 2: global max pooling layer
gmp = tf.reduce_max(conv, reduction_indices=[1], name='gmp')
不同核尺寸卷积操作：
kernel_sizes = [3,4,5] # 分别用窗口大小为3/4/5的卷积核
with tf.name_scope("mul_cnn"):
pooled_outputs = []
for kernel_size in kernel_sizes:
# CNN layer
conv = tf.layers.conv1d(embedding_inputs, self.config.num_filters, kernel_size, name='conv-%s' % kernel_size)
# global max pooling layer
gmp = tf.reduce_max(conv, reduction_indices=[1], name='gmp')
pooled_outputs.append(gmp)
self.h_pool = tf.concat(pooled_outputs, 1) #池化后进行拼接