RNN与情感分类问题实战-加载IMDB数据集
作者:互联网
目录
- Sentiment Analysis
- Two approaches
- Single layer
- Multi-layers
Sentiment Analysis
Two approaches
SimpleRNNCell
single layer
multi-layers
RNNCell
Single layer
import os import tensorflow as tf import numpy as np from tensorflow import keras from tensorflow.keras import layers tf.random.set_seed(22) np.random.seed(22) os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' assert tf.__version__.startswith('2.') batchsz = 128 # the most frequest words total_words = 10000 max_review_len = 80 embedding_len = 100 (x_train, y_train), (x_test, y_test) = keras.datasets.imdb.load_data(num_words=total_words) # x_train:[b, 80] # x_test: [b, 80] x_train = keras.preprocessing.sequence.pad_sequences(x_train, maxlen=max_review_len) x_test = keras.preprocessing.sequence.pad_sequences(x_test, maxlen=max_review_len) db_train = tf.data.Dataset.from_tensor_slices((x_train, y_train)) db_train = db_train.shuffle(1000).batch(batchsz, drop_remainder=True) db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test)) db_test = db_test.batch(batchsz, drop_remainder=True) print('x_train shape:', x_train.shape, tf.reduce_max(y_train), tf.reduce_min(y_train)) print('x_test shape:', x_test.shape) class MyRNN(keras.Model): def __init__(self, units): super(MyRNN, self).__init__() # [b, 64] self.state0 = [tf.zeros([batchsz, units])] self.state1 = [tf.zeros([batchsz, units])] # transform text to embedding representation # [b, 80] => [b, 80, 100] self.embedding = layers.Embedding(total_words, embedding_len, input_length=max_review_len) # [b, 80, 100] , h_dim: 64 # RNN: cell1 ,cell2, cell3 # SimpleRNN,units=64表示100个向量转成64个初始的状态 self.rnn_cell0 = layers.SimpleRNNCell(units, dropout=0.5) self.rnn_cell1 = layers.SimpleRNNCell(units, dropout=0.5) # fc, [b, 80, 100] => [b, 64] => [b, 1] self.outlayer = layers.Dense(1) def call(self, inputs, training=None): """ net(x) net(x, training=True) :train mode net(x, training=False): test :param inputs: [b, 80] :param training: :return: """ # [b, 80] x = inputs # embedding: [b, 80] => [b, 80, 100] x = self.embedding(x) # rnn cell compute # [b, 80, 100] => [b, 64] state0 = self.state0 state1 = self.state1 for word in tf.unstack(x, axis=1): # word: [b, 100] # h1 = x*wxh+h0*whh # out0: [b, 64] out0, state0 = self.rnn_cell0(word, state0, training) # out1: [b, 64] out1, state1 = self.rnn_cell1(out0, state1, training) # out: [b, 64] => [b, 1] x = self.outlayer(out1) # p(y is pos|x) prob = tf.sigmoid(x) return prob def main(): units = 64 epochs = 4 model = MyRNN(units) model.compile(optimizer=keras.optimizers.Adam(0.001), loss=tf.losses.BinaryCrossentropy(), metrics=['accuracy']) model.fit(db_train, epochs=epochs, validation_data=db_test) model.evaluate(db_test) if __name__ == '__main__': main()
Multi-layers
import os import tensorflow as tf import numpy as np from tensorflow import keras from tensorflow.keras import layers tf.random.set_seed(22) np.random.seed(22) os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' assert tf.__version__.startswith('2.') batchsz = 128 # the most frequest words total_words = 10000 # 编码10000个单词 max_review_len = 80 # 句子长度80 embedding_len = 100 (x_train, y_train), (x_test, y_test) = keras.datasets.imdb.load_data(num_words=total_words) # x_train:[b, 80] # x_test: [b, 80] x_train = keras.preprocessing.sequence.pad_sequences(x_train, maxlen=max_review_len) x_test = keras.preprocessing.sequence.pad_sequences(x_test, maxlen=max_review_len) db_train = tf.data.Dataset.from_tensor_slices((x_train, y_train)) # drop_remainder,丢弃最后一个大小不合适的batch db_train = db_train.shuffle(1000).batch(batchsz, drop_remainder=True) db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test)) db_test = db_test.batch(batchsz, drop_remainder=True) print('x_train shape:', x_train.shape, tf.reduce_max(y_train), tf.reduce_min(y_train)) print('x_test shape:', x_test.shape) class MyRNN(keras.Model): def __init__(self, units): super(MyRNN, self).__init__() # transform text to embedding representation # [b, 80] => [b, 80, 100] # embedding_len=100表示一个单词为100的向量 self.embedding = layers.Embedding(total_words, embedding_len, input_length=max_review_len) # [b, 80, 100] , h_dim: 64 self.rnn = keras.Sequential([ layers.SimpleRNN(units, dropout=0.5, return_sequences=True, unroll=True), layers.SimpleRNN(units, dropout=0.5, unroll=True) ]) # fc, [b, 80, 100] => [b, 64] => [b, 1] # 得到分类结果 self.outlayer = layers.Dense(1) def call(self, inputs, training=None): """ net(x) net(x, training=True) :train mode net(x, training=False): test :param inputs: [b, 80] :param training: 计算过程是train还是test :return: """ # [b, 80] x = inputs # embedding: [b, 80] => [b, 80, 100] x = self.embedding(x) # rnn cell compute # x: [b, 80, 100] => [b, 64] x = self.rnn(x) # out: [b, 64] => [b, 1] x = self.outlayer(x) # p(y is pos|x) prob = tf.sigmoid(x) return prob def main(): units = 64 epochs = 4 model = MyRNN(units) model.compile(optimizer=keras.optimizers.Adam(0.001), loss=tf.losses.BinaryCrossentropy(), metrics=['accuracy']) model.fit(db_train, epochs=epochs, validation_data=db_test) model.evaluate(db_test) if __name__ == '__main__': main()
标签:RNN,self,db,tf,train,IMDB,test,80,加载 来源: https://blog.51cto.com/u_13804357/2709173