tensorflow实现循环神经网络

一.循环核

二.RNN实现字母预测。

2.1 输入一个字母预测下个字母

该例实现对于a,b,c,d,e五个字母，对于5个字母进行训练，要求最终可以通过输入字母a网络可以输出b,输入b网络预测出c，…。对于5个字母进行one-hot编码

import tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Dense, SimpleRNN
import matplotlib.pyplot as plt
import os

os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
input_word = "abcde"
w_to_id = {'a': 0, 'b': 1, 'c': 2, 'd': 3, 'e': 4}  # 单词映射到数值id的词典
id_to_onehot = {0: [1., 0., 0., 0., 0.], 1: [0., 1., 0., 0., 0.], 2: [0., 0., 1., 0., 0.], 3: [0., 0., 0., 1., 0.],
                4: [0., 0., 0., 0., 1.]}  # id编码为one-hot

x_train = [id_to_onehot[w_to_id['a']], id_to_onehot[w_to_id['b']], id_to_onehot[w_to_id['c']],
           id_to_onehot[w_to_id['d']], id_to_onehot[w_to_id['e']]]
y_train = [w_to_id['b'], w_to_id['c'], w_to_id['d'], w_to_id['e'], w_to_id['a']]

np.random.seed(7)
np.random.shuffle(x_train)
np.random.seed(7)
np.random.shuffle(y_train)
tf.random.set_seed(7)

# 使x_train符合SimpleRNN输入要求：[送入样本数， 循环核时间展开步数， 每个时间步输入特征个数]。
# 此处整个数据集送入，送入样本数为len(x_train)；输入1个字母出结果，循环核时间展开步数为1; 表示为独热码有5个输入特征，每个时间步输入特征个数为5
x_train = np.reshape(x_train, (len(x_train), 1, 5))
y_train = np.array(y_train)

model = tf.keras.Sequential([
    SimpleRNN(3),
    Dense(5, activation='softmax')
])

model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "E:\pythoncode\deeplearning\checkpoint\Rnn_1.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True,
                                                 monitor='loss')  # 由于fit没有给出测试集，不计算测试集准确率，根据loss，保存最优模型

history = model.fit(x_train, y_train, batch_size=32, epochs=100, callbacks=[cp_callback])

model.summary()

# print(model.trainable_variables)
# file = open('./weights.txt', 'w')  # 参数提取
# for v in model.trainable_variables:
#     file.write(str(v.name) + '\n')
#     file.write(str(v.shape) + '\n')
#     file.write(str(v.numpy()) + '\n')
# file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
loss = history.history['loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.title('Training Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.title('Training Loss')
plt.legend()
plt.show()

############### predict #############

preNum = int(input("input the number of test alphabet:"))
for i in range(preNum):
    alphabet1 = input("input test alphabet:")
    alphabet = [id_to_onehot[w_to_id[alphabet1]]]
    # 使alphabet符合SimpleRNN输入要求：[送入样本数， 循环核时间展开步数， 每个时间步输入特征个数]。此处验证效果送入了1个样本，送入样本数为1；输入1个字母出结果，所以循环核时间展开步数为1; 表示为独热码有5个输入特征，每个时间步输入特征个数为5
    alphabet = np.reshape(alphabet, (1, 1, 5))
    result = model.predict([alphabet])
    pred = tf.argmax(result, axis=1)
    pred = int(pred)
    tf.print(alphabet1 + '->' + input_word[pred])

输出结果：

2.2 连续输入4个字母预测下个字母

输入：a,b,c,d预测e. 输入：b,c,d,e 预测出a.
这里的4个Wxh权重矩阵一样，循环核4步后输出预测结果

import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, SimpleRNN
import matplotlib.pyplot as plt
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
input_word = "abcde"
w_to_id = {'a': 0, 'b': 1, 'c': 2, 'd': 3, 'e': 4}  # 单词映射到数值id的词典
id_to_onehot = {0: [1., 0., 0., 0., 0.], 1: [0., 1., 0., 0., 0.], 2: [0., 0., 1., 0., 0.], 3: [0., 0., 0., 1., 0.],
                4: [0., 0., 0., 0., 1.]}  # id编码为one-hot

x_train = [
    [id_to_onehot[w_to_id['a']], id_to_onehot[w_to_id['b']], id_to_onehot[w_to_id['c']], id_to_onehot[w_to_id['d']]],
    [id_to_onehot[w_to_id['b']], id_to_onehot[w_to_id['c']], id_to_onehot[w_to_id['d']], id_to_onehot[w_to_id['e']]],
    [id_to_onehot[w_to_id['c']], id_to_onehot[w_to_id['d']], id_to_onehot[w_to_id['e']], id_to_onehot[w_to_id['a']]],
    [id_to_onehot[w_to_id['d']], id_to_onehot[w_to_id['e']], id_to_onehot[w_to_id['a']], id_to_onehot[w_to_id['b']]],
    [id_to_onehot[w_to_id['e']], id_to_onehot[w_to_id['a']], id_to_onehot[w_to_id['b']], id_to_onehot[w_to_id['c']]],
]
y_train = [w_to_id['e'], w_to_id['a'], w_to_id['b'], w_to_id['c'], w_to_id['d']]

np.random.seed(7)
np.random.shuffle(x_train)
np.random.seed(7)
np.random.shuffle(y_train)
tf.random.set_seed(7)

# 使x_train符合SimpleRNN输入要求：[送入样本数， 循环核时间展开步数， 每个时间步输入特征个数]。
# 此处整个数据集送入，送入样本数为len(x_train)；输入4个字母出结果，循环核时间展开步数为4; 表示为独热码有5个输入特征，每个时间步输入特征个数为5
x_train = np.reshape(x_train, (len(x_train), 4, 5))
y_train = np.array(y_train)

model = tf.keras.Sequential([
    SimpleRNN(3),
    Dense(5, activation='softmax')
])

model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "E:\pythoncode\deeplearning\checkpoint\Rnn_onehot_4pre1.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True,
                                                 monitor='loss')  # 由于fit没有给出测试集，不计算测试集准确率，根据loss，保存最优模型

history = model.fit(x_train, y_train, batch_size=32, epochs=100, callbacks=[cp_callback])

model.summary()

# # print(model.trainable_variables)
# file = open('./weights.txt', 'w')  # 参数提取
# for v in model.trainable_variables:
#     file.write(str(v.name) + '\n')
#     file.write(str(v.shape) + '\n')
#     file.write(str(v.numpy()) + '\n')
# file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
loss = history.history['loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.title('Training Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.title('Training Loss')
plt.legend()
plt.show()

############### predict #############

preNum = int(input("input the number of test alphabet:"))
for i in range(preNum):
    alphabet1 = input("input test alphabet:")
    alphabet = [id_to_onehot[w_to_id[a]] for a in alphabet1]
    # 使alphabet符合SimpleRNN输入要求：[送入样本数， 循环核时间展开步数， 每个时间步输入特征个数]。此处验证效果送入了1个样本，送入样本数为1；输入4个字母出结果，所以循环核时间展开步数为4; 表示为独热码有5个输入特征，每个时间步输入特征个数为5
    alphabet = np.reshape(alphabet, (1, 4, 5))
    result = model.predict([alphabet])
    pred = tf.argmax(result, axis=1)
    pred = int(pred)
    tf.print(alphabet1 + '->' + input_word[pred])

输出:

三.embdding编码

用embedding编码重新编写上面的输入4个连续字母预测下一个字母。
这里扩大数据集，对26个字母都进行编码。26个字母按照顺序22中不同的连续序列，从abcd->e,…,vwxy->z.

import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, SimpleRNN, Embedding
import matplotlib.pyplot as plt
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
input_word = "abcdefghijklmnopqrstuvwxyz"
w_to_id = {'a': 0, 'b': 1, 'c': 2, 'd': 3, 'e': 4,
           'f': 5, 'g': 6, 'h': 7, 'i': 8, 'j': 9,
           'k': 10, 'l': 11, 'm': 12, 'n': 13, 'o': 14,
           'p': 15, 'q': 16, 'r': 17, 's': 18, 't': 19,
           'u': 20, 'v': 21, 'w': 22, 'x': 23, 'y': 24, 'z': 25}  # 单词映射到数值id的词典

training_set_scaled = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
                       11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
                       21, 22, 23, 24, 25]

x_train = []
y_train = []
#设置训练数据为4个连续字母，输出为后一个字母，总共22组。eg:abcd->e,...,vwxy->z.
for i in range(4, 26):
    x_train.append(training_set_scaled[i - 4:i])
    y_train.append(training_set_scaled[i])

np.random.seed(7)
np.random.shuffle(x_train)
np.random.seed(7)
np.random.shuffle(y_train)
tf.random.set_seed(7)

# 使x_train符合Embedding输入要求：[送入样本数， 循环核时间展开步数] ，
# 此处整个数据集送入所以送入，送入样本数为len(x_train)；输入4个字母出结果，循环核时间展开步数为4。
x_train = np.reshape(x_train, (len(x_train), 4))
y_train = np.array(y_train)

model = tf.keras.Sequential([
    Embedding(26, 2),
    SimpleRNN(10),
    Dense(26, activation='softmax')
])

model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "E:\pythoncode\deeplearning\checkpoint\Rnn_embedding_4pre1.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True,
                                                 monitor='loss')  # 由于fit没有给出测试集，不计算测试集准确率，根据loss，保存最优模型

history = model.fit(x_train, y_train, batch_size=32, epochs=100, callbacks=[cp_callback])

model.summary()

# file = open('./weights.txt', 'w')  # 参数提取
# for v in model.trainable_variables:
#     file.write(str(v.name) + '\n')
#     file.write(str(v.shape) + '\n')
#     file.write(str(v.numpy()) + '\n')
# file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
loss = history.history['loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.title('Training Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.title('Training Loss')
plt.legend()
plt.show()

################# predict ##################

preNum = int(input("input the number of test alphabet:"))
for i in range(preNum):
    alphabet1 = input("input test alphabet:")
    alphabet = [w_to_id[a] for a in alphabet1]
    # 使alphabet符合Embedding输入要求：[送入样本数， 时间展开步数]。
    # 此处验证效果送入了1个样本，送入样本数为1；输入4个字母出结果，循环核时间展开步数为4。
    alphabet = np.reshape(alphabet, (1, 4))
    result = model.predict([alphabet])
    pred = tf.argmax(result, axis=1)
    pred = int(pred)
    tf.print(alphabet1 + '->' + input_word[pred])

输出：