textcnn自己的理解
来源:互联网 发布:深圳市超惠转网络推广 编辑:程序博客网 时间:2024/05/29 09:49
import tensorflow as tfimport numpy as npclass TextCNN(object): """ A CNN for text classification. Uses an embedding layer, followed by a convolutional, max-pooling and softmax layer. """ # sequence_length-最长词汇数 # num_classes-分类数 # vocab_size-总词汇数 # embedding_size-词向量长度 # filter_sizes-卷积核尺寸3,4,5 # num_filters-卷积核数量 # l2_reg_lambda-l2正则化系数 def __init__( self, sequence_length, num_classes, vocab_size, embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0): # Placeholders for input, output and dropout self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x") self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y") self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob") # Keeping track of l2 regularization loss (optional) l2_loss = tf.constant(0.0) # Embedding layer with tf.device('/cpu:0'), tf.name_scope("embedding"): self.W = tf.Variable( #19758 128 tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0), name="W") #input_x %len(w) self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x) #add one vector # 添加一个维度,[batch_size, sequence_length, embedding_size, 1] self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1) # Create a convolution + maxpool layer for each filter size pooled_outputs = [] #3 4 5 for i, filter_size in enumerate(filter_sizes): with tf.name_scope("conv-maxpool-%s" % filter_size): # Convolution Layer 3,128,1,2 filter_shape = [filter_size, embedding_size, 1, num_filters] #随机生成正太分布 W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W") # # 2 b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b") conv = tf.nn.conv2d( self.embedded_chars_expanded, W, strides=[1, 1, 1, 1], padding="VALID", name="conv") # Apply nonlinearity h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu") # Maxpooling over the outputs # 56 -(3,4,5) + 1 pooled = tf.nn.max_pool( h, ksize=[1, sequence_length - filter_size + 1, 1, 1], strides=[1, 1, 1, 1], padding='VALID', name="pool") pooled_outputs.append(pooled) # Combine all the pooled features #将pooled_outputs中的值全部取出来然后reshape成[len(input_x),num_filters*len(filters_size)],然后进行了dropout层防止过拟合, #最后再添加了一层全连接层与softmax层将特征映射成不同类别上的概率 #2 3 把池化层输出变成一维向量 num_filters_total = num_filters * len(filter_sizes) self.h_pool = tf.concat(pooled_outputs, 3) # , 6 self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total]) # Add dropout with tf.name_scope("dropout"): self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob) # Final (unnormalized) scores and predictions with tf.name_scope("output"): #6,2 W = tf.get_variable( "W", shape=[num_filters_total, num_classes], initializer=tf.contrib.layers.xavier_initializer()) b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b") #l2 way l2_loss += tf.nn.l2_loss(W) l2_loss += tf.nn.l2_loss(b) #computes matmul(x, weights) + biases. self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores") self.predictions = tf.argmax(self.scores, 1, name="predictions") # CalculateMean cross-entropy loss with tf.name_scope("loss"): #Computes softmax cross entropy between `logits` and `labels`. losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y) #计算张量的尺寸的元素平均值。 self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss # Accuracy with tf.name_scope("accuracy"): correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1)) self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")
(一) flag:
分测试和验证集:0.1
文件路径
model:
embedding128
fileter 3,4,5
num_filters 128
dropout 0.5
L20.0
trainpaameters:
batch_size 64
num_epochs 200
evalute_every 100
checkpoint(保存模型用的)100
num_checkpoints number of checkpoints to save 5
misc parameters
soft_placement true
log_device false
加载数据。
建造词库。
一句话最长的句子 56
vocab_processor (相当于wordembedding)
打乱数据。
分测试和验证集
获得最长的 句子 56
y有两种结果
vocab_size 18758
设置global_step
optimizer
gradients去计算loss
设置变量去跟踪梯度。
把x,y合在一起,然后去分批
在分解。
给train模型
需要x,y,dropout
调用textcnn模型
x:1066,56
y: 1066 ,2
dropout: 0.5
input_x:
w:19758,128
为什么embedded-chars:106656 128
W=[19758,128]属于-1,1之间。
Embedded_chars:1066 56 128
embedded_chars_expanded 1066 56 128 1
conv2d函数:
embedded_charss_expanded1066 56 128 1
w: 3,128,1,2
得到( ,2)
传递调优和loss梯度,global,记录梯度,loss,准确率
- textcnn自己的理解
- TextCNN
- 补码-自己的理解
- 自己理解的Fragment
- 封装自己的理解
- zookeeper自己的理解
- 自己理解的KMP
- CSRF自己的理解!!
- 自己的理解JVM
- 自己理解的GMF
- 自己理解的算法
- SpringMVC自己的理解
- MyBatis自己的理解
- Spring自己的理解
- maven自己的理解
- Dagger2自己的理解
- Yoon Kim的textCNN讲解,以及tensorflow实现,CNN文本分类
- java数据源的理解---------------自己的理解
- vs2015编译和调试linux程序
- Java:接口编程题:写出如下UML表示的接口和类的代码(有A、B、C三个接口,和play、show 方法)
- 排序算法二:快速排序算法原理以及MATLAB与Python实现
- vue mint-ui组件的下拉刷新插件 mt-loadmore 取消下拉
- C语言实现平衡二叉树
- textcnn自己的理解
- JZOJ1414. 平台(2017.8B组)
- python 飞机大战
- [bzoj1598][Usaco2008 Mar]牛跑步
- palindrome-partitioning
- 5个强大的Java分布式缓存框架
- numpy入门——基础运算
- Spring MVC 解读——<mvc:annotation-driven/>
- 剑指offer-17- 二叉树后序遍历