本文实现连续输入四个字母预测下一个字母的例子:
废话不多说,直接上代码:
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense,SimpleRNN,Embedding
import matplotlib.pyplot as plt
import os
import PySide2
dirname = os.path.dirname(PySide2.__file__)
plugin_path = os.path.join(dirname, 'plugins', 'platforms')
os.environ['QT_QPA_PLATFORM_PLUGIN_PATH'] = plugin_path
input_word = "abcdefghijkmnopqrstuvwxyz"
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} # 单词隐射到数值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 = []
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SimpleRNN输入要求:【送入样本数,循环和时间展开步数, 每个时间步输入特征个数】
# 此处整个数据集送入数以送入,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
x_train = np.reshape(x_train, (len(x_train), 4))
y_train = np.array(y_train)
model = tf.keras.Sequential([
Embedding(26, 2), # 这一层会生成一个五行两列的可训练参数矩阵,实现编码可训练
SimpleRNN(10),
Dense(26, activation='softmax')
])
model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
loss=tf.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
checkpoint_save_path = './checkpoint/mnist.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保存最有模型
history = model.fit(x_train, y_train, batch_size=32, epochs=50, callbacks=[cp_callback])
model.summary()
# print(model.trainable_variables)
file = open('./weights.txt', 'w')
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 num of test alphabet:"))
for i in range(preNum):
alphabet1 = input("input test alphabet1:")
alphabet = [w_to_id[a] for a in alphabet1]
# 使alphabet符合SimpleRNN输入要求:【送入样本数, 循环时间展开步数,每个时间步输入特征个数】
# 此处验证效果送入了一个岩本,送入样本数为1;输入1个字母出结果,所哟循环核时间展开步数为1,表示为独热吗有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))
result = model.predict([alphabet])
pred = tf.argmax(result, axis=1)
pred = int(pred)
tf.print(alphabet1 + '->' + input_word[pred])
预测结果: