深度学习2.0-40.LSTM原理及实战 原创

1147-柳同学

发表文章数:593

首页 » 算法 » 正文

1.LSTM原理

深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创

深度学习2.0-40.LSTM原理及实战
                    原创
深度学习2.0-40.LSTM原理及实战
                    原创

2.LSTM的实战

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
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)
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)

# 修改两处self.state0与self.rnn_cell0
class MyRNN(keras.Model):

    def __init__(self, units):
        super(MyRNN, self).__init__()

        # [b, 64]
        self.state0 = [tf.zeros([batchsz, units]), tf.zeros([batchsz, units])]
        self.state1 = [tf.zeros([batchsz, units]), 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

        self.rnn_cell0 = layers.LSTMCell(units, dropout=0.5)
        self.rnn_cell1 = layers.LSTMCell(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

    import time

    t0 = time.time()

    model = MyRNN(units)
    model.compile(optimizer=keras.optimizers.Adam(0.001),
                  loss=tf.losses.BinaryCrossentropy(),
                  metrics=['accuracy'],
                  experimental_run_tf_function=False)
    model.fit(db_train, epochs=epochs, validation_data=db_test)

    model.evaluate(db_test)

    t1 = time.time()
    # 64.3 seconds, 83.4%
    print('total time cost:', t1 - t0)


if __name__ == '__main__':
    main()
import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
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)
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__()

        # 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
        self.rnn = keras.Sequential([
            layers.LSTM(units, dropout=0.5, return_sequences=True, unroll=True),
            layers.LSTM(units, dropout=0.5, unroll=True)
        ])

        # 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
        # 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

    import time

    t0 = time.time()

    model = MyRNN(units)
    model.compile(optimizer=keras.optimizers.Adam(0.001),
                  loss=tf.losses.BinaryCrossentropy(),
                  metrics=['accuracy'],
                  experimental_run_tf_function=False
                  )

    model.fit(db_train, epochs=epochs, validation_data=db_test)

    model.evaluate(db_test)

    t1 = time.time()
    # 69.3 secnods, 83%
    print('total time cost:', t1 - t0)


if __name__ == '__main__':
    main()
    

未经允许不得转载:作者:1147-柳同学, 转载或复制请以 超链接形式 并注明出处 拜师资源博客
原文地址:《深度学习2.0-40.LSTM原理及实战 原创》 发布于2021-02-05

分享到:
赞(0) 打赏

评论 抢沙发

评论前必须登录!

  注册



长按图片转发给朋友

觉得文章有用就打赏一下文章作者

支付宝扫一扫打赏

微信扫一扫打赏

Vieu3.3主题
专业打造轻量级个人企业风格博客主题!专注于前端开发,全站响应式布局自适应模板。

登录

忘记密码 ?

您也可以使用第三方帐号快捷登录

Q Q 登 录
微 博 登 录