以下是一个简单的 TextCNN 模型的代码示例：
```python
import tensorflow as tf
class TextCNN(object):
def __init__(self, sequence_length, num_classes, vocab_size, embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):
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")
l2_loss = tf.constant(0.0)
# Embedding layer
with tf.device('/cpu:0'), tf.name_scope("embedding"):
self.W = tf.Variable(tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0), name="W")
self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
# Convolution + maxpool layer
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# Convolution layer
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
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
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
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pooled_outputs, 3)
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"):
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_loss += tf.nn.l2_loss(W)
l2_loss += tf.nn.l2_loss(b)
self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.predictions = tf.argmax(self.scores, 1, name="predictions")
# Calculate mean cross-entropy loss
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss
```
注释：
- `sequence_length`：句子的最大长度。
- `num_classes`：分类的类别数。
- `vocab_size`：词汇表的大小。
- `embedding_size`：嵌入层的维度。
- `filter_sizes`：卷积核的大小列表。
- `num_filters`：每个卷积核的数量。
- `l2_reg_lambda`：L2 正则化系数。
该模型包括以下步骤：
1. 嵌入层：将输入的整数序列转换为嵌入向量。使用 `tf.nn.embedding_lookup()` 函数查找嵌入矩阵中的对应嵌入向量。
2. 卷积层：使用不同大小的卷积核对嵌入向量进行卷积操作。每个卷积核产生一个特征图，表示在句子中找到的某种模式。
3. 池化层：对于每个特征图，使用 max-pooling 操作来提取最显著的特征。
4. Dropout：在全连接层之前，使用 dropout 操作来减少过拟合。
5. 全连接层：将所有特征图连接起来，然后进行分类。
最低0.47元/天 解锁文章
392
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
